`

First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring


Challenge results

Task description

The aim of this task is to develop anomalous sound detection techniques that can train models on new data with noisy normal machine sounds and a few additional samples containing only factory noise or clean normal machine sounds, enabling the model to achieve higher detection performance regardless of environmental noise shifts or other domain shifts.

More detailed task description can be found in the task description page

Teams ranking

Table including only the best performing system per submitting team.

Rank Submission Information Evaluation Dataset Development Dataset
Submission Code Technical
Report
Official
Rank
Official
Score
AutoTrash
(AUC)
AutoTrash
(pAUC)
BandSealer
(AUC)
BandSealer
(pAUC)
CoffeeGrinder
(AUC)
CoffeeGrinder
(pAUC)
HomeCamera
(AUC)
HomeCamera
(pAUC)
Polisher
(AUC)
Polisher
(pAUC)
ScrewFeeder
(AUC)
ScrewFeeder
(pAUC)
ToyPet
(AUC)
ToyPet
(pAUC)
ToyRCCar
(AUC)
ToyRCCar
(pAUC)
ToyCar
(AUC)
ToyCar
(pAUC)
ToyTrain
(AUC)
ToyTrain
(pAUC)
Bearing
(AUC)
Bearing
(pAUC)
Fan
(AUC)
Fan
(pAUC)
Gearbox
(AUC)
Gearbox
(pAUC)
Slider
(AUC)
Slider
(pAUC)
Valve
(AUC)
Valve
(pAUC)
DCASE2025_baseline_task2_MAHALA DCASE2025baseline2025 58 56.50558189601554 ± 0.0012582648036794197 62.59 54.16 45.77 49.11 52.52 51.42 57.05 51.84 60.34 53.79 75.85 70.05 58.88 56.84 55.67 54.00 62.04 49.05 48.51 48.32 61.33 61.86 58.27 50.82 62.44 55.07 62.03 53.61 58.61 52.53
Zhou_XJU_task2_4 ZhouXJU2025 93 52.90746388052138 ± 0.0012225858948732692 43.95 51.11 56.27 52.32 46.38 52.16 55.68 53.74 53.42 50.58 64.00 57.11 54.77 53.42 54.61 52.00 78.38 55.53 69.87 55.16 61.44 54.53 58.09 56.32 70.46 61.63 62.74 51.68 75.63 72.53
Cai_NCUT_task2_3 CaiNCUT2025 42 57.5585903081211 ± 0.0013141680391751025 75.94 61.29 57.92 54.89 45.84 52.63 48.52 50.26 55.57 51.24 83.40 67.08 59.64 58.13 59.46 52.50 69.44 53.32 73.72 55.32 66.09 62.21 53.11 51.16 57.27 54.68 68.61 56.05 80.89 73.76
Saengthong_SCITOK_task2_2 SaengthongSCITOK2025 2 61.569433614253896 ± 0.001484160042616686 86.06 71.05 62.38 57.37 53.23 52.00 52.37 52.32 67.40 56.68 84.26 73.47 67.11 57.84 52.95 51.63 67.34 55.68 77.11 59.79 65.99 60.32 54.49 56.95 68.31 58.74 70.23 57.05 81.46 72.00
Zhang_DKU_task2_4 ZhangDKU2025 63 55.76153468345078 ± 0.001174199773801252 82.96 65.21 56.49 51.84 55.43 51.74 45.76 55.32 58.53 54.21 68.19 56.42 52.26 52.26 47.27 50.79 66.16 48.47 68.14 50.10 70.10 56.00 57.99 53.36 81.59 73.84 72.78 55.63 85.40 86.94
WT_IACAS_task2_2 WTIACAS2025 44 57.44073696264025 ± 0.0013512115891784388 87.27 72.74 66.85 61.37 50.12 51.63 50.36 52.89 57.79 56.63 66.48 62.84 59.16 55.00 42.32 51.21 70.94 59.84 77.96 58.84 69.98 63.11 61.70 55.42 83.20 74.26 71.78 55.74 91.24 85.53
Zhou_XAUAT_task2_1 ZhouXAUAT2025 24 58.1881454965969 ± 0.001303450752882116 90.58 79.16 55.62 50.63 55.14 51.84 62.03 55.32 62.74 54.05 52.52 51.42 61.85 53.58 51.29 54.79 63.90 53.58 71.25 52.89 63.25 59.11 63.60 61.32 73.87 57.00 63.82 52.16 79.53 68.16
Zhong_USTC_task2_4 ZhongUSTC2025 30 57.874646573614505 ± 0.0013941667172153518 81.32 56.10 55.96 55.21 58.76 55.68 49.43 52.05 70.54 62.16 76.01 63.53 59.49 54.74 41.59 49.32 67.49 54.24 62.69 52.67 60.26 63.58 55.37 49.68 60.16 56.24 62.44 57.98 68.88 61.13
Vijayyan_SNUC_task2_1 VijayyanSNUC2025 109 49.90505686153821 ± 0.0012811394826572587 64.39 56.74 41.16 48.32 45.70 50.53 34.37 47.37 53.20 51.32 72.65 63.47 51.10 52.89 48.03 49.89 63.24 49.05 62.76 54.32 65.14 58.32 57.58 51.58 63.38 54.74 64.14 53.05 81.16 63.16
CHUNG_KUCAU_task2_4 CHUNGKUCAU2025 47 57.227161466047036 ± 0.0013105905782118228 77.48 67.68 67.33 56.95 48.55 51.16 63.55 57.84 56.18 52.37 74.23 67.32 47.25 47.58 46.82 51.37 66.81 51.36 70.31 558.78 72.06 57.00 51.06 51.31 61.06 52.57 65.06 50.15 78.40 67.78
Dung_CNTT1PTIT_task2_1 DungCNTT1PTIT2025 112 48.71892564275941 ± 0.0011303602632511981 38.71 54.58 50.06 48.68 54.41 51.74 51.51 51.05 51.62 50.58 43.46 49.11 43.03 48.68 54.54 52.47 48.32 52.63 50.39 50.26 52.78 53.95 52.22 50.58 50.47 63.32 46.94 51.21 46.73 49.53
Zhang_NWPU_task2_2 ZhangNWPU2025 67 55.42463764307989 ± 0.0013394739153165399 65.80 56.95 64.48 55.95 51.36 50.84 55.55 55.11 62.68 58.32 62.28 57.53 62.47 58.32 36.46 47.95 66.58 49.32 74.98 53.53 73.08 63.53 62.60 59.16 73.08 60.21 76.20 54.74 82.10 67.95
Chao_BUCT_task2_3 ChaoBUCT2025 108 50.13154697532129 ± 0.001259520077091061 56.74 50.26 37.40 48.58 70.57 50.95 60.64 52.11 52.78 51.79 41.29 48.63 51.41 48.47 45.98 49.63 48.48 42.68 54.16 53.70 58.36 58.13 52.54 51.92 49.20 47.76 52.73 52.69 52.47 52.64
Li_XJTLU_task2_2 LiXJTLU2025 87 53.469426047012206 ± 0.0012893785514650324 76.28 68.11 52.38 51.11 42.51 52.05 53.29 53.63 52.59 50.00 54.35 50.05 52.99 51.00 56.24 49.89 68.73 53.05 66.72 57.30 58.16 50.68 57.63 48.15 55.83 54.00 60.24 52.73 75.80 64.73
Wang_ZJU_task2_4 WangZJU2025 55 56.866003688314095 ± 0.001245781793743034 62.41 54.53 47.02 50.05 53.62 51.84 55.58 52.32 59.04 55.00 72.29 67.58 59.15 57.00 59.98 54.84 55.38 60.16 43.75 50.37 56.36 52.88 58.27 60.16 62.12 54.57 61.64 51.84 54.34 64.68
Lin_IASP_task2_4 LinIASP2025 73 54.776114357402165 ± 0.0011741700736731956 77.88 69.58 47.76 51.16 52.12 51.42 48.18 49.74 53.30 53.26 61.41 58.74 54.74 54.68 54.49 50.47 59.73 50.67 60.99 49.68 62.39 59.73 59.72 55.78 60.18 57.47 60.20 53.15 67.18 59.38
Lobanov_ITMO_task2_2 LobanovITMO2025 98 52.52595001212435 ± 0.001248375343145035 66.47 62.26 58.00 49.89 43.83 51.74 57.19 52.89 52.98 50.42 52.88 49.74 47.93 51.21 49.63 49.16 42.54 2550.00 63.52 3988.00 52.66 57.22 55.26 55.10 53.70 54.12 43.84 45.07 65.80 65.80
Qian_nivic_task2_2 Qiannivic2025 28 58.01974104378345 ± 0.0014035588713639333 82.51 56.10 57.63 53.47 56.22 51.58 46.67 53.32 68.13 61.26 75.28 64.47 59.28 54.53 48.30 49.11 64.23 51.53 60.88 55.30 63.58 65.32 56.81 50.22 59.73 56.21 63.31 53.87 69.04 59.39
Wang_MYPS_task2_3 WangMYPS2025 1 61.62755928284949 ± 0.0013535025717832298 80.61 77.05 64.22 51.63 57.94 52.16 62.45 53.79 68.76 54.05 90.24 79.16 62.64 54.05 44.35 52.84 66.22 50.74 62.10 54.63 62.41 65.68 56.98 51.60 60.18 57.75 62.34 53.08 68.66 62.28
Emon_HDK_task2_1 EmonHDK2025 121 45.15099353175931 ± 0.0012413329586015724 30.49 52.26 35.37 48.47 70.66 52.21 46.39 52.68 43.90 49.58 53.52 48.58 37.77 48.32 46.00 51.84 72.55 65.40 90.05 83.60 94.20 85.80 67.35 67.50 86.35 50.80 92.15 70.30 85.95 61.40
Fu_CUMT_task2_4 FuCUMT2025 26 58.13668049404887 ± 0.0014644138554073664 82.07 56.10 55.06 54.95 60.47 57.53 48.92 49.32 69.41 62.95 75.01 63.26 55.68 55.37 46.10 50.11 65.22 54.44 62.06 53.99 61.73 63.65 58.73 54.06 62.35 53.25 61.84 54.52 68.70 61.88
Ding_HFUU_task2_4 DingHFUU2025 59 56.37774443771024 ± 0.001224450673236013 65.98 51.95 46.57 49.47 53.42 52.11 52.68 52.21 58.71 53.89 70.26 67.84 59.27 57.32 59.16 54.32 62.80 49.70 58.81 50.19 58.94 58.12 58.55 61.05 61.86 50.63 61.67 55.05 64.66 57.35
Yang_NBU_task2_1 YangNBU2025 3 61.20134568401735 ± 0.0013249535881398125 84.76 75.37 66.41 57.79 50.09 49.63 62.99 53.37 75.64 61.32 94.22 80.00 56.83 53.21 42.80 49.74 64.06 51.79 61.85 55.90 63.34 63.56 58.19 49.97 59.95 53.25 63.96 56.00 68.71 58.42
Kret_CU_task2_1 KretCU2025 115 47.90299388774425 ± 0.001155154341464739 32.60 48.42 50.35 50.32 45.49 49.26 33.00 49.63 51.97 51.21 61.04 62.79 56.35 54.74 59.08 49.79 47.78 0.00 56.94 13.60 50.76 13.20 51.64 0.80 58.10 0.00 56.12 5.20 55.00 3.60
Zheng_SJTU-AITHU_task2_2 ZhengSJTU-AITHU2025 11 59.49972264254595 ± 0.0013491175199334372 94.60 85.58 68.09 58.95 52.27 47.58 56.31 55.32 58.22 54.37 67.21 53.21 64.23 56.00 47.46 52.95 66.15 53.16 73.63 57.63 67.60 58.79 61.96 55.89 82.57 67.53 84.90 59.95 90.82 84.11
Zhao_CUMT_task2_3 ZhaoCUMT2025 61 56.05710040362136 ± 0.0013546424429837578 59.85 51.05 48.25 50.89 51.73 50.26 51.71 53.37 62.63 56.84 80.06 68.63 51.79 54.26 59.71 54.21 60.14 48.84 48.57 48.74 61.26 63.21 55.85 50.32 61.96 54.53 61.93 52.58 54.28 51.31
Ozeki_MELCO_task2_1 OzekiMELCO2025 23 58.23359688192865 ± 0.0011667802614379898 86.35 74.79 62.04 55.79 46.36 51.05 56.50 50.63 62.40 55.63 52.30 49.42 64.14 56.89 62.21 55.11 58.16 51.52 71.56 49.68 56.63 53.10 54.53 53.73 61.90 56.94 73.65 59.52 82.78 73.26
Huang_XJU_task2_1 HuangXJU2025 25 58.14052430128241 ± 0.0012193313166606692 74.01 53.63 57.15 59.37 46.98 49.21 65.68 52.79 52.08 50.42 82.14 69.32 61.78 57.68 54.54 51.00 66.22 53.63 72.08 56.16 75.86 64.95 59.20 50.58 72.02 58.32 65.55 54.21 76.20 74.74
Fujimura_NU_task2_1 FujimuraNU2025 7 59.99466314801132 ± 0.001325555756111588 78.10 65.53 74.27 61.84 50.36 52.00 64.66 53.68 61.79 58.47 83.84 68.89 57.33 57.05 41.64 51.89 67.08 48.63 72.48 56.79 77.74 57.21 53.60 52.05 72.86 60.58 66.99 54.47 92.52 82.58
Jiang_THUEE_task2_2 JiangTHUEE2025 10 59.79329753333621 ± 0.0013522826832875893 94.98 86.21 67.95 58.26 52.66 47.37 54.77 55.89 59.64 54.68 70.12 56.89 64.66 56.37 46.94 51.47 66.90 53.00 72.71 55.95 68.93 60.58 61.91 55.00 81.95 68.32 85.56 60.26 92.04 86.37
Bian_TGU_task2_3 BianTGU2025 104 51.417480569726926 ± 0.0011698485309061142 44.25 49.79 55.13 50.89 49.26 51.05 57.35 51.63 46.36 48.16 57.37 51.84 52.45 51.68 55.26 51.53 48.09 48.52 46.53 49.63 49.90 49.16 52.63 50.94 52.80 49.53 55.24 51.16 48.80 51.74
Sera_TMU_task2_1 SeraTMU2025 57 56.567561042877735 ± 0.0013602097930091965 57.68 52.00 52.72 54.05 60.92 53.21 51.90 50.58 49.11 49.47 83.39 67.21 59.66 55.74 60.14 51.32 71.28 54.63 73.08 57.42 67.80 61.36 56.06 51.79 71.52 62.42 67.38 49.42 69.48 56.63
Kim_DAU_task2_2 KimDAU2025 111 48.96578012474582 ± 0.0011669517429796642 59.12 49.16 44.24 50.84 40.06 49.89 57.76 56.05 47.59 50.11 49.97 51.95 45.08 48.11 47.18 50.37 77.58 66.87 77.83 68.42 78.50 69.53 77.43 65.33 78.30 69.64 77.21 64.10 78.81 67.27
Wang_UniS_task2_1 WangUniS2025 34 57.754303274825524 ± 0.0012838059463938772 86.59 72.84 58.69 55.00 50.61 51.26 60.86 54.11 54.32 53.05 58.10 52.84 63.87 57.63 50.19 53.84 60.74 49.95 66.68 50.53 52.89 50.11 56.02 53.11 71.89 72.65 78.14 56.63 86.38 78.32
Guan_HEU_task2_1 GuanHEU2025 22 58.25344060002535 ± 0.0011865451404030904 70.81 59.53 55.51 53.63 46.55 49.58 49.38 50.74 61.83 56.11 89.98 77.26 62.19 61.79 55.60 51.89 72.19 54.65 75.44 57.42 64.71 61.51 56.81 53.06 70.24 57.79 67.58 53.80 73.35 65.50
Kim_AISTAT_task2_4 KimAISTAT2025 29 57.95495072758183 ± 0.0013606493522197662 90.21 77.47 55.11 54.53 50.96 55.32 69.84 61.53 51.39 51.63 59.97 51.58 63.67 55.79 47.60 50.47 65.72 50.42 75.68 61.68 66.04 55.58 62.08 51.84 74.80 66.89 82.20 63.79 78.12 70.42


Supplementary metrics (recall, precision, and F1 score)

Rank Submission Information Evaluation Dataset
Submission Code Technical
Report
Official
Rank
AutoTrash
(F1 score)
AutoTrash
(Recall)
AutoTrash
(Precision)
BandSealer
(F1 score)
BandSealer
(Recall)
BandSealer
(Precision)
CoffeeGrinder
(F1 score)
CoffeeGrinder
(Recall)
CoffeeGrinder
(Precision)
HomeCamera
(F1 score)
HomeCamera
(Recall)
HomeCamera
(Precision)
Polisher
(F1 score)
Polisher
(Recall)
Polisher
(Precision)
ScrewFeeder
(F1 score)
ScrewFeeder
(Recall)
ScrewFeeder
(Precision)
ToyPet
(F1 score)
ToyPet
(Recall)
ToyPet
(Precision)
ToyRCCar
(F1 score)
ToyRCCar
(Recall)
ToyRCCar
(Precision)
DCASE2025_baseline_task2_MAHALA DCASE2025baseline2025 58 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Zhou_XJU_task2_4 ZhouXJU2025 93 28.65 18.15 68.06 54.38 51.43 57.69 34.63 24.37 59.82 58.48 54.10 63.64 51.58 49.81 53.48 58.70 58.85 58.55 49.70 43.93 57.21 54.00 54.00 54.00
Cai_NCUT_task2_3 CaiNCUT2025 42 68.43 63.55 74.11 50.77 47.08 55.09 35.00 24.44 61.65 55.29 54.84 55.75 53.30 48.07 59.80 75.28 73.42 77.24 52.10 42.93 66.26 54.58 54.84 54.32
Saengthong_SCITOK_task2_2 SaengthongSCITOK2025 2 80.32 76.68 84.32 42.25 29.76 72.81 47.48 38.18 62.78 28.11 19.09 53.30 56.48 46.47 71.98 69.92 97.96 54.36 64.37 74.08 56.91 42.21 35.10 52.94
Zhang_DKU_task2_4 ZhangDKU2025 63 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
WT_IACAS_task2_2 WTIACAS2025 44 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Zhou_XAUAT_task2_1 ZhouXAUAT2025 24 82.05 84.71 79.56 54.81 55.36 54.27 55.75 62.60 50.24 57.69 60.00 55.56 65.82 78.00 56.93 63.10 75.95 53.96 62.51 73.78 54.22 56.57 68.44 48.20
Zhong_USTC_task2_4 ZhongUSTC2025 30 51.94 51.92 51.96 55.01 54.98 55.04 46.96 46.98 46.94 52.78 52.53 53.03 56.97 56.98 56.96 54.90 54.84 54.96 53.91 53.93 53.89 51.49 51.69 51.30
Vijayyan_SNUC_task2_1 VijayyanSNUC2025 109 70.88 82.02 62.40 52.53 48.41 57.42 36.52 31.84 42.81 49.20 49.65 48.75 50.07 45.77 55.27 69.36 94.99 54.62 62.46 70.13 56.30 33.33 25.55 47.94
CHUNG_KUCAU_task2_4 CHUNGKUCAU2025 47 48.92 33.92 87.72 42.98 30.71 71.58 48.73 38.40 66.67 58.06 48.00 73.47 38.43 27.00 66.67 67.86 72.65 63.67 57.12 58.23 56.04 25.44 17.78 44.69
Dung_CNTT1PTIT_task2_1 DungCNTT1PTIT2025 112 64.40 94.99 48.72 46.78 42.79 51.60 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Zhang_NWPU_task2_2 ZhangNWPU2025 67 58.76 49.35 72.58 46.85 45.91 47.83 53.06 52.00 54.17 49.94 48.82 51.11 52.87 51.69 54.11 51.42 50.04 52.88 52.01 50.98 53.08 51.02 50.00 52.08
Chao_BUCT_task2_3 ChaoBUCT2025 108 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
Li_XJTLU_task2_2 LiXJTLU2025 87 69.14 68.64 69.65 55.00 54.98 55.02 32.62 24.00 50.91 46.06 44.88 47.30 51.84 48.44 55.76 49.85 49.41 50.30 46.97 41.21 54.60 53.73 51.43 56.25
Wang_ZJU_task2_4 WangZJU2025 55 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Lin_IASP_task2_4 LinIASP2025 73 64.35 64.48 64.23 52.48 51.31 53.70 54.98 54.11 55.88 47.37 47.67 47.08 51.67 50.72 52.66 56.96 56.84 57.08 50.85 50.08 51.65 54.32 54.11 54.53
Lobanov_ITMO_task2_2 LobanovITMO2025 98 68.53 98.99 52.41 44.89 37.89 55.05 32.17 25.71 42.96 23.17 14.12 64.52 34.63 27.87 45.73 28.07 19.20 52.17 32.60 25.87 44.04 43.62 38.57 50.19
Qian_nivic_task2_2 Qiannivic2025 28 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Wang_MYPS_task2_3 WangMYPS2025 1 73.43 71.89 75.04 59.46 59.40 59.52 52.00 51.47 52.54 59.97 59.93 60.01 61.98 61.74 62.22 83.02 82.99 83.05 59.02 58.33 59.73 44.00 43.64 44.36
Emon_HDK_task2_1 EmonHDK2025 121 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 6.81 3.69 43.64 10.70 6.40 32.65 13.95 8.40 41.18 0.00 0.00 0.00 11.91 6.77 49.44
Fu_CUMT_task2_4 FuCUMT2025 26 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Ding_HFUU_task2_4 DingHFUU2025 59 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Yang_NBU_task2_1 YangNBU2025 3 51.92 51.92 51.92 47.61 47.25 47.97 51.85 51.69 52.01 44.05 43.91 44.19 53.01 52.98 53.04 49.92 49.92 49.92 42.00 42.00 42.00 52.89 52.83 52.95
Kret_CU_task2_1 KretCU2025 115 0.00 0.00 0.00 6.79 3.69 42.11 41.83 36.98 48.15 57.10 61.11 53.58 24.62 15.65 57.69 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
Zheng_SJTU-AITHU_task2_2 ZhengSJTU-AITHU2025 11 85.81 85.26 86.38 64.07 63.75 64.39 48.81 47.69 49.98 56.05 55.93 56.17 57.37 56.90 57.85 61.96 61.94 61.98 56.81 55.52 58.16 45.88 42.67 49.61
Zhao_CUMT_task2_3 ZhaoCUMT2025 61 61.50 60.85 62.16 20.92 13.22 50.17 17.33 11.16 38.71 22.16 13.33 65.57 32.73 24.00 51.43 0.00 0.00 0.00 42.91 41.48 44.44 0.00 0.00 0.00
Ozeki_MELCO_task2_1 OzekiMELCO2025 23 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Huang_XJU_task2_1 HuangXJU2025 25 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Fujimura_NU_task2_1 FujimuraNU2025 7 66.89 100.00 50.25 68.19 75.95 61.86 0.00 0.00 0.00 48.60 38.77 65.12 5.19 2.67 100.00 66.67 100.00 50.00 62.57 70.74 56.09 66.67 100.00 50.00
Jiang_THUEE_task2_2 JiangTHUEE2025 10 88.81 88.09 89.54 64.15 63.75 64.56 50.81 49.81 51.85 55.02 54.98 55.06 57.53 56.90 58.18 65.72 65.76 65.68 58.14 56.95 59.38 46.35 43.92 49.07
Bian_TGU_task2_3 BianTGU2025 104 16.27 9.60 53.33 24.95 15.75 60.00 14.76 8.40 60.87 31.33 22.61 50.98 0.00 0.00 0.00 25.51 15.75 67.02 20.33 12.31 58.39 0.00 0.00 0.00
Sera_TMU_task2_1 SeraTMU2025 57 0.00 0.00 0.00 7.17 3.75 81.08 0.00 0.00 0.00 20.00 12.00 60.00 7.01 3.69 68.57 32.79 20.00 90.91 0.00 0.00 0.00 18.43 10.91 59.41
Kim_DAU_task2_2 KimDAU2025 111 48.79 45.96 52.00 16.34 9.75 50.32 54.26 62.40 48.00 58.03 73.42 47.97 55.43 60.98 50.81 19.29 12.92 38.01 28.39 19.80 50.13 25.63 18.20 43.33
Wang_UniS_task2_1 WangUniS2025 34 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Guan_HEU_task2_1 GuanHEU2025 22 60.06 54.19 67.36 29.70 19.35 63.83 40.13 30.41 58.96 27.05 18.67 49.12 33.04 22.40 62.92 63.91 47.35 98.31 40.52 28.10 72.64 32.35 21.82 62.50
Kim_AISTAT_task2_4 KimAISTAT2025 29 79.88 85.95 74.61 37.03 26.55 61.18 23.80 14.75 61.64 66.81 62.60 71.63 37.38 30.00 49.59 66.89 100.00 50.25 68.24 97.96 52.36 53.17 58.58 48.68



Systems ranking

Rank Submission Information Evaluation Dataset Development Dataset
Submission Code Technical
Report
Official
Rank
Official
Score
AutoTrash
(AUC)
AutoTrash
(pAUC)
BandSealer
(AUC)
BandSealer
(pAUC)
CoffeeGrinder
(AUC)
CoffeeGrinder
(pAUC)
HomeCamera
(AUC)
HomeCamera
(pAUC)
Polisher
(AUC)
Polisher
(pAUC)
ScrewFeeder
(AUC)
ScrewFeeder
(pAUC)
ToyPet
(AUC)
ToyPet
(pAUC)
ToyRCCar
(AUC)
ToyRCCar
(pAUC)
ToyCar
(AUC)
ToyCar
(pAUC)
ToyTrain
(AUC)
ToyTrain
(pAUC)
Bearing
(AUC)
Bearing
(pAUC)
Fan
(AUC)
Fan
(pAUC)
Gearbox
(AUC)
Gearbox
(pAUC)
Slider
(AUC)
Slider
(pAUC)
Valve
(AUC)
Valve
(pAUC)
DCASE2025_baseline_task2_MAHALA DCASE2025baseline2025 58 56.50558189601554 ± 0.0012582648036794197 62.59 54.16 45.77 49.11 52.52 51.42 57.05 51.84 60.34 53.79 75.85 70.05 58.88 56.84 55.67 54.00 62.04 49.05 48.51 48.32 61.33 61.86 58.27 50.82 62.44 55.07 62.03 53.61 58.61 52.53
DCASE2025_baseline_task2_MSE DCASE2025baseline2025 77 54.42827820713174 ± 0.001271407576916618 48.26 54.21 51.06 52.05 55.20 53.42 61.76 52.84 53.29 52.32 65.39 62.11 47.60 55.00 57.36 55.53 62.28 49.70 59.11 50.19 59.84 61.12 54.85 49.46 57.64 52.49 59.44 52.32 65.36 57.35
Zhou_XJU_task2_1 ZhouXJU2025 100 52.416950012493416 ± 0.0011881967859310029 46.52 49.53 54.53 50.89 43.02 50.16 48.82 52.84 54.45 51.42 66.81 59.11 56.14 54.32 55.23 53.32 74.45 56.42 72.63 56.26 61.27 52.63 56.10 54.68 68.90 60.63 62.53 52.16 76.45 74.00
Zhou_XJU_task2_2 ZhouXJU2025 94 52.84774417237518 ± 0.0012060424784515957 45.39 49.53 57.64 51.89 47.06 50.68 48.90 52.95 53.89 51.47 64.51 57.37 56.26 53.79 55.46 53.42 75.06 54.37 71.45 55.47 61.36 53.42 57.61 56.84 69.69 60.42 62.05 52.11 75.54 72.53
Zhou_XJU_task2_3 ZhouXJU2025 96 52.63120572932777 ± 0.001226939985877493 45.07 51.05 54.38 50.47 43.47 51.26 52.96 54.11 53.83 51.05 64.26 59.74 55.00 53.58 56.44 53.74 76.41 57.84 70.77 55.21 61.64 53.37 57.28 55.58 70.54 60.79 62.28 52.47 77.47 73.37
Zhou_XJU_task2_4 ZhouXJU2025 93 52.90746388052138 ± 0.0012225858948732692 43.95 51.11 56.27 52.32 46.38 52.16 55.68 53.74 53.42 50.58 64.00 57.11 54.77 53.42 54.61 52.00 78.38 55.53 69.87 55.16 61.44 54.53 58.09 56.32 70.46 61.63 62.74 51.68 75.63 72.53
Cai_NCUT_task2_1 CaiNCUT2025 45 57.34434703825625 ± 0.0011704510303176085 85.12 66.26 55.49 56.26 44.55 52.47 50.09 50.05 56.70 50.21 79.78 63.84 59.23 58.21 54.73 53.05 71.57 55.63 73.17 55.11 68.21 61.05 52.77 50.37 56.90 53.53 69.17 54.16 81.53 74.84
Cai_NCUT_task2_2 CaiNCUT2025 83 54.05784411973193 ± 0.0012580742078938656 50.26 53.68 53.30 52.63 54.78 52.79 54.91 53.42 54.09 51.11 63.56 58.42 46.96 54.74 57.66 56.32 62.46 49.74 57.57 51.11 57.47 59.89 54.54 49.53 56.03 52.16 58.37 51.32 64.46 58.68
Cai_NCUT_task2_3 CaiNCUT2025 42 57.5585903081211 ± 0.0013141680391751025 75.94 61.29 57.92 54.89 45.84 52.63 48.52 50.26 55.57 51.24 83.40 67.08 59.64 58.13 59.46 52.50 69.44 53.32 73.72 55.32 66.09 62.21 53.11 51.16 57.27 54.68 68.61 56.05 80.89 73.76
Saengthong_SCITOK_task2_1 SaengthongSCITOK2025 84 53.81478512150386 ± 0.0013067715610662351 56.90 54.68 51.40 54.21 45.53 50.89 38.31 50.26 62.41 53.00 78.80 67.32 57.30 58.00 53.69 52.74 69.31 54.37 78.20 60.53 65.70 60.21 59.86 51.63 64.84 56.21 69.80 56.58 81.99 73.58
Saengthong_SCITOK_task2_2 SaengthongSCITOK2025 2 61.569433614253896 ± 0.001484160042616686 86.06 71.05 62.38 57.37 53.23 52.00 52.37 52.32 67.40 56.68 84.26 73.47 67.11 57.84 52.95 51.63 67.34 55.68 77.11 59.79 65.99 60.32 54.49 56.95 68.31 58.74 70.23 57.05 81.46 72.00
Saengthong_SCITOK_task2_3 SaengthongSCITOK2025 56 56.63642648298707 ± 0.0011745609201499784 73.11 58.11 58.62 55.74 45.14 50.42 48.13 50.21 42.69 49.16 91.26 81.63 66.58 57.68 59.03 52.89 67.85 52.21 74.38 54.53 61.53 60.84 53.07 50.95 60.11 52.84 67.82 55.47 77.11 71.47
Saengthong_SCITOK_task2_4 SaengthongSCITOK2025 80 54.32596489450181 ± 0.0013284693479479592 51.83 50.89 54.48 52.79 45.82 50.42 45.48 50.05 65.83 56.00 72.32 61.89 57.44 59.16 53.23 52.32 66.99 50.53 77.32 55.21 59.30 56.74 58.43 49.00 62.73 57.63 69.04 59.89 76.48 67.58
Zhang_DKU_task2_1 ZhangDKU2025 88 53.4615898288795 ± 0.001179781217054352 68.01 60.11 51.87 54.58 58.40 51.84 41.09 52.05 53.32 51.05 64.13 54.05 53.12 52.11 48.46 50.84 67.80 52.68 71.21 52.10 65.24 58.10 54.92 53.05 80.70 69.36 66.31 53.47 85.73 85.63
Zhang_DKU_task2_2 ZhangDKU2025 70 55.18393915462276 ± 0.0012646610416560881 83.81 67.21 48.62 51.00 56.66 50.58 46.64 52.00 56.82 53.58 59.96 54.00 54.57 53.11 53.89 50.21 69.27 49.78 69.63 49.31 71.60 61.31 59.42 55.26 81.64 70.00 66.06 52.73 84.77 85.89
Zhang_DKU_task2_3 ZhangDKU2025 92 52.9797667433996 ± 0.0011534403766833834 75.94 57.21 55.94 52.11 41.86 48.84 51.58 54.63 59.23 56.53 61.80 56.47 52.19 50.05 40.91 49.53 68.69 49.68 71.00 50.42 71.08 56.21 57.75 53.21 84.36 76.15 72.37 55.57 86.47 87.73
Zhang_DKU_task2_4 ZhangDKU2025 63 55.76153468345078 ± 0.001174199773801252 82.96 65.21 56.49 51.84 55.43 51.74 45.76 55.32 58.53 54.21 68.19 56.42 52.26 52.26 47.27 50.79 66.16 48.47 68.14 50.10 70.10 56.00 57.99 53.36 81.59 73.84 72.78 55.63 85.40 86.94
WT_IACAS_task2_1 WTIACAS2025 66 55.53360456952694 ± 0.0012887031567615573 79.64 67.26 64.70 58.58 51.79 53.11 50.89 52.95 56.33 57.16 59.06 56.53 55.40 53.95 40.24 50.84 67.16 54.95 78.26 58.42 68.78 62.26 59.96 54.42 83.34 74.05 72.24 56.26 90.18 76.05
WT_IACAS_task2_2 WTIACAS2025 44 57.44073696264025 ± 0.0013512115891784388 87.27 72.74 66.85 61.37 50.12 51.63 50.36 52.89 57.79 56.63 66.48 62.84 59.16 55.00 42.32 51.21 70.94 59.84 77.96 58.84 69.98 63.11 61.70 55.42 83.20 74.26 71.78 55.74 91.24 85.53
WT_IACAS_task2_3 WTIACAS2025 86 53.52111771682423 ± 0.001301200447333405 69.92 64.84 60.59 57.74 50.11 51.95 50.48 52.79 52.69 55.21 52.31 53.26 53.84 54.63 41.53 50.89 67.88 54.68 78.26 58.11 69.36 62.74 59.96 53.63 81.38 71.11 71.84 56.32 87.44 72.37
WT_IACAS_task2_4 WTIACAS2025 76 54.440119451520474 ± 0.001310278439474516 72.73 66.32 60.53 58.89 48.68 51.63 50.11 53.16 52.99 54.26 53.48 55.53 56.89 56.42 43.96 52.32 70.86 58.33 78.72 59.21 71.20 63.00 62.52 55.63 80.44 71.84 71.02 56.26 86.76 76.89
Zhou_XAUAT_task2_1 ZhouXAUAT2025 24 58.1881454965969 ± 0.001303450752882116 90.58 79.16 55.62 50.63 55.14 51.84 62.03 55.32 62.74 54.05 52.52 51.42 61.85 53.58 51.29 54.79 63.90 53.58 71.25 52.89 63.25 59.11 63.60 61.32 73.87 57.00 63.82 52.16 79.53 68.16
Zhou_XAUAT_task2_2 ZhouXAUAT2025 43 57.509962813993454 ± 0.0012796350724583706 90.53 79.68 53.19 50.21 56.85 52.89 63.58 54.63 60.72 53.63 49.32 51.21 58.37 54.63 52.05 53.63 65.48 53.37 66.67 50.53 64.05 60.26 64.58 59.84 70.63 54.68 62.03 52.32 73.25 58.89
Zhou_XAUAT_task2_3 ZhouXAUAT2025 95 52.66336603046757 ± 0.0011874412147661675 85.40 77.00 56.64 50.74 39.75 49.42 49.24 51.16 56.84 53.95 37.91 48.53 58.06 52.47 58.12 53.79 65.56 53.95 63.54 48.58 61.79 57.47 62.00 57.00 63.61 59.89 62.14 50.84 77.21 60.16
Zhou_XAUAT_task2_4 ZhouXAUAT2025 50 57.09208791484903 ± 0.001355863605136462 91.60 81.63 57.87 51.16 57.92 49.84 60.10 56.05 64.21 53.89 49.99 51.05 53.84 51.74 47.63 53.47 59.63 51.68 68.05 52.11 66.83 59.63 64.16 60.84 72.00 60.58 64.80 54.05 80.42 69.58
Zhong_USTC_task2_1 ZhongUSTC2025 54 56.89623750195928 ± 0.0013847743865767457 77.92 75.05 59.39 55.21 49.96 50.26 49.43 52.05 66.75 57.42 74.49 58.95 59.49 54.74 41.59 49.32 65.81 52.51 62.88 52.11 63.08 65.25 56.36 49.76 59.91 56.11 64.43 52.91 69.78 60.35
Zhong_USTC_task2_2 ZhongUSTC2025 51 57.068368795617666 ± 0.001397800488455209 81.32 56.10 59.39 55.21 49.96 50.26 49.43 52.05 70.54 62.16 76.01 63.53 59.49 54.74 41.59 49.32 64.70 49.98 61.41 52.80 64.25 63.50 59.37 51.23 60.67 57.53 62.92 54.99 70.83 60.66
Zhong_USTC_task2_3 ZhongUSTC2025 38 57.69762462723721 ± 0.0013868286522009086 77.92 75.05 55.96 55.21 58.76 55.68 49.43 52.05 66.75 57.42 74.49 58.95 59.49 54.74 41.59 49.32 64.52 53.14 62.48 52.97 64.53 65.64 55.95 52.13 58.55 58.48 64.58 56.25 69.82 59.29
Zhong_USTC_task2_4 ZhongUSTC2025 30 57.874646573614505 ± 0.0013941667172153518 81.32 56.10 55.96 55.21 58.76 55.68 49.43 52.05 70.54 62.16 76.01 63.53 59.49 54.74 41.59 49.32 67.49 54.24 62.69 52.67 60.26 63.58 55.37 49.68 60.16 56.24 62.44 57.98 68.88 61.13
Vijayyan_SNUC_task2_1 VijayyanSNUC2025 109 49.90505686153821 ± 0.0012811394826572587 64.39 56.74 41.16 48.32 45.70 50.53 34.37 47.37 53.20 51.32 72.65 63.47 51.10 52.89 48.03 49.89 63.24 49.05 62.76 54.32 65.14 58.32 57.58 51.58 63.38 54.74 64.14 53.05 81.16 63.16
CHUNG_KUCAU_task2_1 CHUNGKUCAU2025 97 52.53513672830565 ± 0.0011797106011080367 68.48 53.84 44.70 50.68 44.63 48.32 49.44 50.63 55.70 52.26 75.68 65.63 51.37 51.16 46.33 48.74 66.06 51.15 70.45 52.31 66.80 54.05 58.80 56.47 74.47 68.10 70.84 53.53 76.96 56.57
CHUNG_KUCAU_task2_2 CHUNGKUCAU2025 65 55.55388801652549 ± 0.0013144380478823914 77.77 66.42 55.63 53.63 54.64 55.84 56.95 54.26 54.23 51.63 57.98 51.37 55.47 50.16 47.72 48.84 65.38 52.68 71.20 56.57 68.85 52.42 57.30 55.36 69.75 54.36 69.42 53.57 74.34 58.63
CHUNG_KUCAU_task2_3 CHUNGKUCAU2025 72 54.77830306706913 ± 0.0012185601690566305 64.68 56.95 49.34 55.16 45.04 49.53 57.41 55.68 55.94 53.68 77.10 68.61 51.41 51.47 48.92 51.32 66.14 51.31 67.25 53.78 66.86 54.94 51.94 52.31 70.28 58.94 63.04 50.73 78.06 65.31
CHUNG_KUCAU_task2_4 CHUNGKUCAU2025 47 57.227161466047036 ± 0.0013105905782118228 77.48 67.68 67.33 56.95 48.55 51.16 63.55 57.84 56.18 52.37 74.23 67.32 47.25 47.58 46.82 51.37 66.81 51.36 70.31 558.78 72.06 57.00 51.06 51.31 61.06 52.57 65.06 50.15 78.40 67.78
Dung_CNTT1PTIT_task2_1 DungCNTT1PTIT2025 112 48.71892564275941 ± 0.0011303602632511981 38.71 54.58 50.06 48.68 54.41 51.74 51.51 51.05 51.62 50.58 43.46 49.11 43.03 48.68 54.54 52.47 48.32 52.63 50.39 50.26 52.78 53.95 52.22 50.58 50.47 63.32 46.94 51.21 46.73 49.53
Zhang_NWPU_task2_1 ZhangNWPU2025 103 51.63482668025466 ± 0.001309776511596873 41.53 52.42 64.58 55.47 52.83 50.11 57.37 58.00 62.86 56.42 58.46 55.58 57.11 58.74 31.15 48.42 66.74 49.47 75.10 53.11 72.30 61.05 62.70 59.84 77.40 60.11 76.92 58.47 83.70 58.72
Zhang_NWPU_task2_2 ZhangNWPU2025 67 55.42463764307989 ± 0.0013394739153165399 65.80 56.95 64.48 55.95 51.36 50.84 55.55 55.11 62.68 58.32 62.28 57.53 62.47 58.32 36.46 47.95 66.58 49.32 74.98 53.53 73.08 63.53 62.60 59.16 73.08 60.21 76.20 54.74 82.10 67.95
Zhang_NWPU_task2_3 ZhangNWPU2025 75 54.535850370502445 ± 0.0013342853613838863 63.40 57.68 64.20 54.68 51.38 51.05 55.59 56.00 62.95 59.26 62.17 57.47 61.29 58.42 33.08 47.63 65.98 49.26 75.04 53.26 72.34 62.47 63.10 60.37 75.42 57.89 75.48 56.32 82.62 70.16
Zhang_NWPU_task2_4 ZhangNWPU2025 82 54.27870089612588 ± 0.0013452482191526702 65.71 58.58 64.13 55.16 51.08 51.05 54.44 55.63 61.53 58.63 57.85 56.37 60.82 58.53 33.86 47.68 66.84 49.42 74.48 53.32 72.60 62.53 62.90 59.74 74.48 57.05 74.76 54.79 82.58 68.47
Chao_BUCT_task2_1 ChaoBUCT2025 118 47.24303918388332 ± 0.0012259541569508577 57.41 52.68 41.93 49.79 67.56 51.47 48.86 49.11 54.92 51.79 31.34 48.58 44.98 49.26 39.18 49.68 48.45 49.50 49.10 50.90 53.70 54.10 54.30 50.20 68.65 47.70 54.85 50.40 59.15 47.70
Chao_BUCT_task2_2 ChaoBUCT2025 114 48.45174273659997 ± 0.001176212566092576 53.46 48.92 44.62 50.69 42.21 48.91 37.75 51.92 53.29 52.39 61.71 51.62 50.96 49.23 44.67 49.65 55.50 50.40 48.50 48.70 56.00 55.70 53.00 50.30 49.50 49.90 49.00 49.10 77.00 62.90
Chao_BUCT_task2_3 ChaoBUCT2025 108 50.13154697532129 ± 0.001259520077091061 56.74 50.26 37.40 48.58 70.57 50.95 60.64 52.11 52.78 51.79 41.29 48.63 51.41 48.47 45.98 49.63 48.48 42.68 54.16 53.70 58.36 58.13 52.54 51.92 49.20 47.76 52.73 52.69 52.47 52.64
Li_XJTLU_task2_1 LiXJTLU2025 89 53.298245047211815 ± 0.0012918346317037904 76.28 68.11 48.51 51.53 42.51 52.05 55.24 50.05 60.21 50.95 54.35 50.05 52.99 51.00 50.95 49.79 68.73 53.05 69.35 55.10 58.22 50.78 50.65 54.21 59.23 51.78 63.95 51.10 75.81 66.99
Li_XJTLU_task2_2 LiXJTLU2025 87 53.469426047012206 ± 0.0012893785514650324 76.28 68.11 52.38 51.11 42.51 52.05 53.29 53.63 52.59 50.00 54.35 50.05 52.99 51.00 56.24 49.89 68.73 53.05 66.72 57.30 58.16 50.68 57.63 48.15 55.83 54.00 60.24 52.73 75.80 64.73
Li_XJTLU_task2_3 LiXJTLU2025 106 50.87625772429204 ± 0.0012462737985353197 67.74 57.74 46.34 51.63 48.25 52.37 46.24 48.37 46.78 49.95 45.75 48.37 58.63 54.42 52.16 50.26 66.31 51.52 62.82 51.78 48.73 52.47 52.37 48.36 57.37 52.36 59.50 49.57 77.25 69.78
Li_XJTLU_task2_4 LiXJTLU2025 99 52.52280596314458 ± 0.0012961572509312515 63.85 58.16 48.59 52.42 37.24 48.42 47.82 50.63 53.54 49.21 78.03 68.00 56.93 54.42 48.80 50.63 63.63 51.84 73.35 59.85 51.35 55.26 53.96 48.78 63.96 52.68 56.44 51.15 78.47 67.63
Wang_ZJU_task2_1 WangZJU2025 107 50.2293951333291 ± 0.0012299324269494255 33.40 48.53 52.12 52.16 52.76 51.95 45.32 51.21 55.14 52.11 58.16 60.37 47.52 54.95 58.06 56.16 56.80 60.16 60.29 60.16 58.08 52.88 58.80 53.25 60.87 49.32 58.90 50.37 55.99 52.05
Wang_ZJU_task2_2 WangZJU2025 64 55.58902163976555 ± 0.001199770971668403 61.28 53.32 47.72 50.89 50.59 50.37 49.31 51.58 60.14 53.68 74.77 68.47 56.40 55.00 58.76 53.95 56.62 54.57 64.96 53.21 58.03 52.88 60.69 48.82 43.75 48.26 55.14 53.21 56.48 52.85
Wang_ZJU_task2_3 WangZJU2025 85 53.7625220777451 ± 0.0012643280566019437 48.59 53.16 51.56 52.16 55.92 54.05 52.87 53.42 54.12 50.84 62.95 60.74 46.64 54.63 59.11 56.21 61.01 51.89 51.85 50.84 56.13 51.11 55.21 50.05 54.29 51.32 52.33 49.37 46.75 26.08
Wang_ZJU_task2_4 WangZJU2025 55 56.866003688314095 ± 0.001245781793743034 62.41 54.53 47.02 50.05 53.62 51.84 55.58 52.32 59.04 55.00 72.29 67.58 59.15 57.00 59.98 54.84 55.38 60.16 43.75 50.37 56.36 52.88 58.27 60.16 62.12 54.57 61.64 51.84 54.34 64.68
Lin_IASP_task2_1 LinIASP2025 105 51.07645561603922 ± 0.0011762821273072503 56.96 49.47 41.81 51.32 51.43 52.89 55.52 50.84 47.70 51.05 55.13 52.89 50.93 51.89 52.88 48.32 64.72 51.70 64.45 52.33 62.50 59.98 61.28 52.46 50.23 54.61 60.94 51.73 63.55 50.99
Lin_IASP_task2_2 LinIASP2025 78 54.41975154704433 ± 0.001185974404419855 83.90 73.00 47.76 51.16 45.70 50.11 50.34 49.42 58.62 53.05 60.02 58.79 49.50 52.84 54.80 51.95 64.72 51.70 64.45 52.33 62.50 59.98 61.28 52.46 50.23 54.61 60.94 51.73 63.55 50.99
Lin_IASP_task2_3 LinIASP2025 74 54.5484232027357 ± 0.0012131329471837765 82.83 71.37 41.81 51.32 51.93 48.68 48.79 53.42 58.62 53.05 60.98 61.89 47.54 53.05 58.01 54.32 64.72 51.70 64.45 52.33 62.50 59.98 61.28 52.46 50.23 54.61 60.94 51.73 63.55 50.99
Lin_IASP_task2_4 LinIASP2025 73 54.776114357402165 ± 0.0011741700736731956 77.88 69.58 47.76 51.16 52.12 51.42 48.18 49.74 53.30 53.26 61.41 58.74 54.74 54.68 54.49 50.47 59.73 50.67 60.99 49.68 62.39 59.73 59.72 55.78 60.18 57.47 60.20 53.15 67.18 59.38
Lobanov_ITMO_task2_1 LobanovITMO2025 110 49.58100152202029 ± 0.0011822233515733215 40.75 49.84 52.87 51.37 47.16 51.95 50.90 50.53 56.21 51.11 49.33 49.58 43.50 49.58 54.86 54.32 44.58 44.58 66.14 66.14 49.50 49.50 55.32 55.32 55.50 55.50 47.92 47.92 50.68 51.68
Lobanov_ITMO_task2_2 LobanovITMO2025 98 52.52595001212435 ± 0.001248375343145035 66.47 62.26 58.00 49.89 43.83 51.74 57.19 52.89 52.98 50.42 52.88 49.74 47.93 51.21 49.63 49.16 42.54 2550.00 63.52 3988.00 52.66 57.22 55.26 55.10 53.70 54.12 43.84 45.07 65.80 65.80
Qian_nivic_task2_1 Qiannivic2025 32 57.83526242732236 ± 0.001312869954266259 81.16 76.00 57.63 53.47 56.22 51.58 46.67 53.32 64.50 57.21 72.07 58.47 59.28 54.53 48.30 49.11 64.91 50.36 63.45 53.70 64.20 65.43 58.55 52.64 61.70 54.76 62.59 56.57 68.28 61.18
Qian_nivic_task2_2 Qiannivic2025 28 58.01974104378345 ± 0.0014035588713639333 82.51 56.10 57.63 53.47 56.22 51.58 46.67 53.32 68.13 61.26 75.28 64.47 59.28 54.53 48.30 49.11 64.23 51.53 60.88 55.30 63.58 65.32 56.81 50.22 59.73 56.21 63.31 53.87 69.04 59.39
Qian_nivic_task2_3 Qiannivic2025 49 57.129551545366276 ± 0.0013938679187242284 80.45 74.32 57.63 53.47 56.22 51.58 46.51 51.53 63.44 58.84 68.32 52.00 56.49 53.05 49.87 50.95 65.59 50.06 63.96 53.24 63.22 64.61 55.97 50.82 59.56 56.19 62.48 58.19 67.67 61.87
Qian_nivic_task2_4 Qiannivic2025 39 57.66599978958733 ± 0.001406927412209501 81.68 56.10 57.63 53.47 56.22 51.58 46.51 51.53 67.26 63.37 72.62 62.26 56.49 53.05 49.87 50.95 65.94 52.43 59.84 55.76 62.71 64.06 57.77 51.97 62.06 56.26 62.47 56.70 70.52 61.85
Wang_MYPS_task2_1 WangMYPS2025 16 59.265578571777176 ± 0.001423556951490758 80.10 72.00 57.48 50.79 58.90 53.21 47.15 49.47 65.28 51.79 94.24 85.32 60.99 53.58 46.61 52.68 67.27 51.84 62.54 53.64 62.81 67.03 56.33 51.85 59.66 57.60 61.05 55.30 69.09 60.66
Wang_MYPS_task2_2 WangMYPS2025 20 58.80363660036158 ± 0.001420353067640853 83.60 56.10 57.48 50.79 58.90 53.21 47.15 49.47 68.51 55.16 91.15 71.87 60.99 53.58 46.61 52.68 65.06 51.33 64.67 50.24 64.36 63.16 58.05 54.61 60.21 56.11 60.39 54.34 68.68 57.39
Wang_MYPS_task2_3 WangMYPS2025 1 61.62755928284949 ± 0.0013535025717832298 80.61 77.05 64.22 51.63 57.94 52.16 62.45 53.79 68.76 54.05 90.24 79.16 62.64 54.05 44.35 52.84 66.22 50.74 62.10 54.63 62.41 65.68 56.98 51.60 60.18 57.75 62.34 53.08 68.66 62.28
Wang_MYPS_task2_4 WangMYPS2025 4 61.04162543834627 ± 0.0014587410270351347 83.98 56.10 64.22 51.63 57.94 52.16 62.45 53.79 72.62 58.47 87.34 67.89 62.64 54.05 44.35 52.84 65.33 51.54 63.27 54.07 63.58 65.39 58.05 51.76 61.39 54.39 60.31 54.30 69.78 58.53
Emon_HDK_task2_1 EmonHDK2025 121 45.15099353175931 ± 0.0012413329586015724 30.49 52.26 35.37 48.47 70.66 52.21 46.39 52.68 43.90 49.58 53.52 48.58 37.77 48.32 46.00 51.84 72.55 65.40 90.05 83.60 94.20 85.80 67.35 67.50 86.35 50.80 92.15 70.30 85.95 61.40
Fu_CUMT_task2_1 FuCUMT2025 52 57.0225500546113 ± 0.001410191721154638 80.53 77.16 57.22 56.11 54.84 50.79 48.92 49.32 64.55 58.21 70.00 52.79 55.68 55.37 46.10 50.11 63.70 52.16 62.30 53.41 61.71 61.33 56.37 51.05 61.18 55.03 62.23 56.09 67.24 57.43
Fu_CUMT_task2_2 FuCUMT2025 40 57.58455696377345 ± 0.0014509734792130385 82.07 56.10 57.22 56.11 54.84 50.79 48.92 49.32 69.41 62.95 75.01 63.26 55.68 55.37 46.10 50.11 63.40 51.75 61.55 54.80 61.44 65.71 58.05 53.52 58.87 55.54 62.37 56.47 68.78 59.74
Fu_CUMT_task2_3 FuCUMT2025 41 57.56389841892947 ± 0.0014244611227164524 80.53 77.16 55.06 54.95 60.47 57.53 48.92 49.32 64.55 58.21 70.00 52.79 55.68 55.37 46.10 50.11 65.77 54.18 60.35 50.20 62.01 65.83 56.58 50.85 60.75 55.54 63.00 53.78 65.53 59.04
Fu_CUMT_task2_4 FuCUMT2025 26 58.13668049404887 ± 0.0014644138554073664 82.07 56.10 55.06 54.95 60.47 57.53 48.92 49.32 69.41 62.95 75.01 63.26 55.68 55.37 46.10 50.11 65.22 54.44 62.06 53.99 61.73 63.65 58.73 54.06 62.35 53.25 61.84 54.52 68.70 61.88
Ding_HFUU_task2_1 DingHFUU2025 71 55.13017039561223 ± 0.0012660750733118095 70.25 65.89 44.77 51.00 52.35 51.53 51.44 55.16 60.23 54.05 66.89 56.89 46.79 53.47 59.11 54.58 71.81 50.63 64.14 53.36 58.84 57.58 59.72 55.57 55.58 53.15 72.11 55.57 50.73 50.31
Ding_HFUU_task2_2 DingHFUU2025 81 54.30344227814425 ± 0.0012121148394503214 65.44 60.74 42.99 50.21 56.81 50.89 52.93 55.05 56.89 54.26 71.94 58.47 44.85 51.37 55.38 52.58 72.96 53.68 62.54 53.68 60.08 52.94 60.94 52.10 56.66 51.78 72.96 54.63 54.46 52.21
Ding_HFUU_task2_3 DingHFUU2025 91 53.15844555398661 ± 0.001265833986842346 46.64 52.42 51.76 51.58 54.65 52.84 54.00 52.68 53.21 50.79 61.60 59.47 47.12 54.89 57.49 55.74 62.29 49.89 58.17 50.69 55.02 60.63 54.66 49.84 57.48 53.10 59.26 51.73 64.73 57.11
Ding_HFUU_task2_4 DingHFUU2025 59 56.37774443771024 ± 0.001224450673236013 65.98 51.95 46.57 49.47 53.42 52.11 52.68 52.21 58.71 53.89 70.26 67.84 59.27 57.32 59.16 54.32 62.80 49.70 58.81 50.19 58.94 58.12 58.55 61.05 61.86 50.63 61.67 55.05 64.66 57.35
Yang_NBU_task2_1 YangNBU2025 3 61.20134568401735 ± 0.0013249535881398125 84.76 75.37 66.41 57.79 50.09 49.63 62.99 53.37 75.64 61.32 94.22 80.00 56.83 53.21 42.80 49.74 64.06 51.79 61.85 55.90 63.34 63.56 58.19 49.97 59.95 53.25 63.96 56.00 68.71 58.42
Yang_NBU_task2_2 YangNBU2025 6 60.44696174623352 ± 0.0014213546943424226 84.52 56.10 66.41 57.79 50.09 49.63 62.99 53.37 78.59 65.84 91.62 70.03 56.83 53.21 42.80 49.74 66.91 51.47 62.55 52.49 62.19 66.72 59.88 49.85 60.66 54.93 62.14 54.12 69.23 57.53
Yang_NBU_task2_3 YangNBU2025 5 60.950192566179204 ± 0.0013762983100007208 83.59 80.21 64.34 55.21 55.03 51.32 64.62 53.58 75.46 60.58 92.60 80.79 55.42 53.63 39.19 50.05 64.70 53.55 60.22 51.57 61.95 66.22 57.96 51.96 60.96 55.16 61.89 56.53 68.79 60.40
Yang_NBU_task2_4 YangNBU2025 8 59.924392523484435 ± 0.0013902482612744536 83.76 56.10 64.34 55.21 55.03 51.32 64.62 53.58 77.39 63.89 89.56 68.53 55.42 53.63 39.19 50.05 67.08 50.26 61.55 55.83 63.87 66.92 58.16 49.70 61.31 54.53 61.99 57.06 71.15 58.99
Kret_CU_task2_1 KretCU2025 115 47.90299388774425 ± 0.001155154341464739 32.60 48.42 50.35 50.32 45.49 49.26 33.00 49.63 51.97 51.21 61.04 62.79 56.35 54.74 59.08 49.79 47.78 0.00 56.94 13.60 50.76 13.20 51.64 0.80 58.10 0.00 56.12 5.20 55.00 3.60
Zheng_SJTU-AITHU_task2_1 ZhengSJTU-AITHU2025 13 59.36979601971116 ± 0.0013888188480768546 91.32 79.74 68.08 58.53 52.22 47.53 57.61 55.58 60.82 54.74 65.11 51.26 63.34 57.00 48.08 52.11 65.52 51.79 75.23 62.11 68.11 60.68 61.97 55.42 78.08 68.79 82.31 60.63 91.04 78.11
Zheng_SJTU-AITHU_task2_2 ZhengSJTU-AITHU2025 11 59.49972264254595 ± 0.0013491175199334372 94.60 85.58 68.09 58.95 52.27 47.58 56.31 55.32 58.22 54.37 67.21 53.21 64.23 56.00 47.46 52.95 66.15 53.16 73.63 57.63 67.60 58.79 61.96 55.89 82.57 67.53 84.90 59.95 90.82 84.11
Zheng_SJTU-AITHU_task2_3 ZhengSJTU-AITHU2025 15 59.31413929500593 ± 0.00135439984680855 95.21 86.79 67.85 57.89 51.25 47.42 56.21 55.05 57.84 54.68 66.53 53.21 63.62 55.89 48.21 52.74 65.94 52.84 72.85 56.53 66.90 58.00 61.90 55.42 83.02 67.79 84.61 59.68 90.46 84.63
Zheng_SJTU-AITHU_task2_4 ZhengSJTU-AITHU2025 12 59.44141398288725 ± 0.0013473754932008504 94.66 85.16 67.95 58.47 52.35 47.58 56.57 55.00 57.82 54.37 67.06 53.58 64.01 55.53 47.65 52.95 66.15 53.11 73.74 57.47 67.32 58.11 61.71 55.79 82.70 67.53 85.02 60.05 90.74 84.11
Zhao_CUMT_task2_1 ZhaoCUMT2025 102 51.65518476016675 ± 0.0011614665718661544 65.29 61.42 53.11 51.95 42.88 49.26 51.70 49.11 42.34 48.47 51.53 52.00 61.41 54.95 51.92 51.00 61.02 52.28 68.78 51.98 71.44 55.16 54.66 52.51 77.94 54.02 62.74 54.07 87.86 53.71
Zhao_CUMT_task2_2 ZhaoCUMT2025 101 52.09351496965263 ± 0.0011749337979479683 61.95 61.26 50.66 50.84 56.21 49.53 43.86 49.74 47.85 50.11 52.72 51.11 58.24 55.68 50.21 49.79 60.74 52.50 67.40 52.14 68.30 55.16 55.14 52.63 75.12 53.88 65.28 53.50 85.30 54.49
Zhao_CUMT_task2_3 ZhaoCUMT2025 61 56.05710040362136 ± 0.0013546424429837578 59.85 51.05 48.25 50.89 51.73 50.26 51.71 53.37 62.63 56.84 80.06 68.63 51.79 54.26 59.71 54.21 60.14 48.84 48.57 48.74 61.26 63.21 55.85 50.32 61.96 54.53 61.93 52.58 54.28 51.31
Zhao_CUMT_task2_4 ZhaoCUMT2025 62 55.78430154315296 ± 0.0012150708201156357 63.72 51.95 51.26 51.63 49.47 51.37 52.51 52.42 57.15 51.63 69.66 66.37 56.50 55.74 58.57 54.00 57.65 49.89 44.92 48.26 59.90 61.84 52.52 51.84 60.70 52.68 60.66 53.53 54.55 51.68
Ozeki_MELCO_task2_1 OzekiMELCO2025 23 58.23359688192865 ± 0.0011667802614379898 86.35 74.79 62.04 55.79 46.36 51.05 56.50 50.63 62.40 55.63 52.30 49.42 64.14 56.89 62.21 55.11 58.16 51.52 71.56 49.68 56.63 53.10 54.53 53.73 61.90 56.94 73.65 59.52 82.78 73.26
Ozeki_MELCO_task2_2 OzekiMELCO2025 60 56.12173861798142 ± 0.0011524809967321202 86.24 71.00 57.86 53.58 43.39 48.95 54.66 50.42 60.31 55.53 51.94 49.74 64.07 54.79 56.06 51.89 61.42 52.10 70.91 50.68 63.04 56.31 55.81 54.89 63.41 55.68 71.11 60.21 81.73 72.31
Ozeki_MELCO_task2_3 OzekiMELCO2025 69 55.29605114517713 ± 0.0011605518223287337 85.94 70.26 57.86 53.58 40.04 49.74 52.02 48.37 60.31 55.53 51.94 49.74 64.09 55.00 56.06 51.89 62.12 51.78 70.79 50.78 63.56 56.42 55.59 54.89 63.55 56.31 71.10 60.63 82.15 74.47
Ozeki_MELCO_task2_4 OzekiMELCO2025 79 54.40720942473768 ± 0.001159342857416225 73.37 58.00 61.00 53.63 47.47 52.58 55.19 50.63 60.11 53.68 46.61 49.11 60.06 50.00 49.65 51.84 55.11 50.84 68.48 55.05 62.69 61.47 54.14 49.52 53.06 53.63 67.54 55.89 81.89 72.47
Huang_XJU_task2_1 HuangXJU2025 25 58.14052430128241 ± 0.0012193313166606692 74.01 53.63 57.15 59.37 46.98 49.21 65.68 52.79 52.08 50.42 82.14 69.32 61.78 57.68 54.54 51.00 66.22 53.63 72.08 56.16 75.86 64.95 59.20 50.58 72.02 58.32 65.55 54.21 76.20 74.74
Huang_XJU_task2_2 HuangXJU2025 27 58.06980771137975 ± 0.0012591353671909718 57.90 49.37 56.38 56.05 68.50 51.63 62.25 51.89 51.69 50.32 78.44 63.11 59.37 59.05 56.31 52.16 64.63 50.21 72.52 58.16 67.98 52.58 57.48 50.63 74.98 60.42 67.23 51.21 73.25 60.21
Huang_XJU_task2_3 HuangXJU2025 35 57.73907728732644 ± 0.0012365379072278196 69.81 52.26 58.29 56.16 48.99 49.42 63.25 51.95 52.93 49.95 81.05 65.68 58.36 58.32 55.21 54.11 67.75 51.84 76.45 62.21 71.90 62.74 57.38 51.16 71.41 57.68 64.08 52.26 76.55 62.47
Huang_XJU_task2_4 HuangXJU2025 37 57.70644391486902 ± 0.0012888105762262749 49.97 48.53 58.08 58.68 68.10 52.21 61.42 52.26 54.04 50.95 80.49 68.11 60.10 57.00 53.46 52.16 66.74 54.05 75.42 56.37 72.04 61.58 58.75 52.21 68.68 59.84 64.14 52.95 79.50 70.21
Fujimura_NU_task2_1 FujimuraNU2025 7 59.99466314801132 ± 0.001325555756111588 78.10 65.53 74.27 61.84 50.36 52.00 64.66 53.68 61.79 58.47 83.84 68.89 57.33 57.05 41.64 51.89 67.08 48.63 72.48 56.79 77.74 57.21 53.60 52.05 72.86 60.58 66.99 54.47 92.52 82.58
Fujimura_NU_task2_2 FujimuraNU2025 21 58.51049267405695 ± 0.0012020424314932898 83.69 61.11 68.46 58.95 48.96 50.89 62.91 55.21 52.05 51.37 82.32 66.11 57.29 58.00 45.19 51.00 66.12 49.05 72.67 55.74 62.39 58.32 55.98 52.95 70.81 56.84 65.44 51.21 85.18 73.63
Fujimura_NU_task2_3 FujimuraNU2025 14 59.343265980019446 ± 0.0012913235359995308 72.97 64.68 73.51 61.89 49.03 49.58 63.42 54.95 57.33 54.95 89.49 73.05 57.88 58.16 42.35 51.53 65.56 49.84 73.36 57.26 69.36 59.26 54.49 52.11 70.28 57.79 68.43 52.21 88.06 78.42
Fujimura_NU_task2_4 FujimuraNU2025 9 59.908156673117766 ± 0.0013659827543125128 75.57 65.00 71.96 60.84 49.00 50.89 64.67 55.26 60.50 55.00 86.90 67.95 57.38 58.89 44.39 52.16 66.97 49.68 73.87 57.37 77.19 61.16 54.14 51.95 71.26 59.32 67.89 50.89 90.68 79.58
Jiang_THUEE_task2_1 JiangTHUEE2025 19 58.89185629814288 ± 0.0012963285929123896 95.16 86.37 66.96 56.95 51.12 47.53 56.28 54.68 55.86 53.95 66.20 53.79 62.34 55.79 48.42 52.47 66.49 52.95 73.28 57.89 66.62 57.16 62.56 55.63 83.75 68.42 84.31 58.84 90.55 83.95
Jiang_THUEE_task2_2 JiangTHUEE2025 10 59.79329753333621 ± 0.0013522826832875893 94.98 86.21 67.95 58.26 52.66 47.37 54.77 55.89 59.64 54.68 70.12 56.89 64.66 56.37 46.94 51.47 66.90 53.00 72.71 55.95 68.93 60.58 61.91 55.00 81.95 68.32 85.56 60.26 92.04 86.37
Jiang_THUEE_task2_3 JiangTHUEE2025 18 59.07396719211147 ± 0.0013421239376490846 95.24 87.11 66.98 56.00 51.98 47.42 54.65 56.16 57.16 54.37 68.41 54.53 64.07 56.00 46.75 51.84 66.42 52.32 73.60 56.26 66.94 58.74 62.56 56.00 82.48 67.16 84.53 58.11 91.66 86.63
Jiang_THUEE_task2_4 JiangTHUEE2025 17 59.155503202726436 ± 0.0013452286475630093 95.77 87.58 66.38 56.32 51.73 47.37 54.22 55.63 57.79 54.21 69.27 55.68 63.56 55.74 47.12 52.21 66.65 52.53 72.92 56.11 67.53 59.42 62.62 56.05 83.01 69.00 84.70 58.53 91.55 86.53
Bian_TGU_task2_1 BianTGU2025 119 46.5757775343439 ± 0.0011764887428223725 47.32 50.21 47.21 49.47 44.21 48.63 39.33 48.37 45.02 51.05 47.52 48.68 48.66 52.42 42.78 50.95 43.45 49.63 48.67 49.47 60.57 65.44 48.76 49.94 56.79 54.05 49.87 51.42 55.25 49.26
Bian_TGU_task2_2 BianTGU2025 116 47.8506175553425 ± 0.0011826605625451974 41.69 49.00 39.99 50.32 49.01 51.42 49.81 49.16 49.53 50.95 47.99 52.53 53.37 49.74 45.61 49.05 42.91 49.47 46.47 49.10 53.55 55.66 51.26 50.26 44.05 51.84 57.75 52.58 47.56 49.10
Bian_TGU_task2_3 BianTGU2025 104 51.417480569726926 ± 0.0011698485309061142 44.25 49.79 55.13 50.89 49.26 51.05 57.35 51.63 46.36 48.16 57.37 51.84 52.45 51.68 55.26 51.53 48.09 48.52 46.53 49.63 49.90 49.16 52.63 50.94 52.80 49.53 55.24 51.16 48.80 51.74
Bian_TGU_task2_4 BianTGU2025 120 46.193399822616286 ± 0.0011813603654829486 49.08 49.79 37.42 49.58 39.25 47.58 48.87 49.74 44.87 48.95 45.85 50.11 46.73 52.16 48.49 49.26 50.82 50.42 53.76 49.58 57.15 54.26 48.18 49.94 52.66 49.00 50.15 49.84 44.24 47.95
Sera_TMU_task2_1 SeraTMU2025 57 56.567561042877735 ± 0.0013602097930091965 57.68 52.00 52.72 54.05 60.92 53.21 51.90 50.58 49.11 49.47 83.39 67.21 59.66 55.74 60.14 51.32 71.28 54.63 73.08 57.42 67.80 61.36 56.06 51.79 71.52 62.42 67.38 49.42 69.48 56.63
Kim_DAU_task2_1 KimDAU2025 113 48.536836193824676 ± 0.0011898932833159556 70.24 52.00 44.41 49.79 57.47 51.95 37.38 49.74 44.11 50.74 45.82 49.95 41.54 48.84 54.86 49.58 56.69 54.11 63.35 50.19 69.25 61.21 60.71 50.47 61.25 64.50 63.13 51.34 73.81 56.42
Kim_DAU_task2_2 KimDAU2025 111 48.96578012474582 ± 0.0011669517429796642 59.12 49.16 44.24 50.84 40.06 49.89 57.76 56.05 47.59 50.11 49.97 51.95 45.08 48.11 47.18 50.37 77.58 66.87 77.83 68.42 78.50 69.53 77.43 65.33 78.30 69.64 77.21 64.10 78.81 67.27
Wang_UniS_task2_1 WangUniS2025 34 57.754303274825524 ± 0.0012838059463938772 86.59 72.84 58.69 55.00 50.61 51.26 60.86 54.11 54.32 53.05 58.10 52.84 63.87 57.63 50.19 53.84 60.74 49.95 66.68 50.53 52.89 50.11 56.02 53.11 71.89 72.65 78.14 56.63 86.38 78.32
Wang_UniS_task2_2 WangUniS2025 46 57.26149732878484 ± 0.001272053328123361 84.68 69.79 58.72 56.63 48.88 51.53 60.96 55.58 54.66 53.05 59.08 51.63 63.96 57.37 47.65 52.63 59.74 44.95 66.06 50.72 53.42 50.23 55.94 53.55 72.21 72.31 78.17 55.19 85.99 78.34
Wang_UniS_task2_3 WangUniS2025 53 56.97485127107289 ± 0.001275596796553062 79.63 63.47 60.64 55.58 49.83 50.05 55.61 53.89 51.49 48.84 65.91 62.42 60.58 57.63 51.57 50.16 55.84 51.00 61.30 49.00 54.61 56.21 54.56 51.53 65.08 56.21 72.92 52.26 78.68 69.26
Wang_UniS_task2_4 WangUniS2025 90 53.19038024532819 ± 0.0012517639544326333 66.09 70.11 51.89 51.63 48.75 52.53 41.70 51.68 54.52 52.68 55.64 47.37 54.85 52.68 58.09 53.16 55.65 50.10 59.83 46.32 52.66 57.89 55.10 51.99 64.17 56.24 72.12 54.34 73.61 66.85
Guan_HEU_task2_1 GuanHEU2025 22 58.25344060002535 ± 0.0011865451404030904 70.81 59.53 55.51 53.63 46.55 49.58 49.38 50.74 61.83 56.11 89.98 77.26 62.19 61.79 55.60 51.89 72.19 54.65 75.44 57.42 64.71 61.51 56.81 53.06 70.24 57.79 67.58 53.80 73.35 65.50
Guan_HEU_task2_2 GuanHEU2025 48 57.2109893578078 ± 0.0011975016881285864 64.38 53.37 54.63 52.95 45.62 50.11 48.62 50.42 61.44 56.00 89.05 75.42 62.38 61.32 55.95 52.11 72.13 55.40 75.86 56.35 67.84 62.57 56.43 50.72 70.36 58.00 66.00 53.16 72.90 63.80
Guan_HEU_task2_3 GuanHEU2025 117 47.50449562562062 ± 0.0011856688491959603 34.21 49.42 42.01 52.11 38.63 49.47 60.67 55.63 48.78 49.84 66.97 56.74 45.84 50.05 44.82 50.00 77.67 61.56 68.48 50.24 59.41 52.21 62.32 52.21 72.50 59.70 68.00 52.47 85.68 72.46
Guan_HEU_task2_4 GuanHEU2025 68 55.31771382417022 ± 0.001333439788966255 57.04 50.00 51.24 54.53 41.12 49.74 53.34 52.26 59.76 55.63 88.68 72.84 58.88 59.11 52.73 51.26 77.06 60.71 74.96 57.36 67.07 60.29 58.73 51.09 72.11 62.52 67.29 52.79 80.62 73.15
Kim_AISTAT_task2_1 KimAISTAT2025 31 57.845411436558095 ± 0.0013619993164548112 89.97 77.47 54.93 54.74 50.89 55.47 70.06 61.32 50.74 51.11 59.19 52.00 64.41 55.68 47.54 50.47 66.12 51.00 75.40 60.42 66.02 56.16 62.14 52.00 73.96 66.53 82.60 64.63 78.82 71.58
Kim_AISTAT_task2_2 KimAISTAT2025 33 57.807994655715866 ± 0.001359971937463962 90.53 78.37 54.48 54.58 50.80 55.32 69.98 61.53 50.65 50.84 59.42 51.47 64.61 54.95 47.62 51.00 66.30 51.63 75.24 60.21 66.30 56.21 62.06 51.79 74.04 66.79 82.50 64.05 78.80 71.63
Kim_AISTAT_task2_3 KimAISTAT2025 36 57.732684643389376 ± 0.0013578163797103682 91.14 78.05 54.49 54.05 50.67 55.00 69.40 61.32 50.75 51.21 59.92 50.84 63.79 54.47 47.92 51.16 65.72 50.68 75.80 61.37 66.26 55.84 62.46 51.84 74.78 66.16 82.62 63.84 78.02 70.26
Kim_AISTAT_task2_4 KimAISTAT2025 29 57.95495072758183 ± 0.0013606493522197662 90.21 77.47 55.11 54.53 50.96 55.32 69.84 61.53 51.39 51.63 59.97 51.58 63.67 55.79 47.60 50.47 65.72 50.42 75.68 61.68 66.04 55.58 62.08 51.84 74.80 66.89 82.20 63.79 78.12 70.42


Supplementary metrics (recall, precision, and F1 score)

Rank Submission Information Evaluation Dataset
Submission Code Technical
Report
Official
Rank
AutoTrash
(F1 score)
AutoTrash
(Recall)
AutoTrash
(Precision)
BandSealer
(F1 score)
BandSealer
(Recall)
BandSealer
(Precision)
CoffeeGrinder
(F1 score)
CoffeeGrinder
(Recall)
CoffeeGrinder
(Precision)
HomeCamera
(F1 score)
HomeCamera
(Recall)
HomeCamera
(Precision)
Polisher
(F1 score)
Polisher
(Recall)
Polisher
(Precision)
ScrewFeeder
(F1 score)
ScrewFeeder
(Recall)
ScrewFeeder
(Precision)
ToyPet
(F1 score)
ToyPet
(Recall)
ToyPet
(Precision)
ToyRCCar
(F1 score)
ToyRCCar
(Recall)
ToyRCCar
(Precision)
DCASE2025_baseline_task2_MAHALA DCASE2025baseline2025 58 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
DCASE2025_baseline_task2_MSE DCASE2025baseline2025 77 65.40 92.47 50.59 63.04 78.20 52.80 58.31 66.67 51.81 67.34 100.00 50.76 64.73 86.07 51.87 66.67 100.00 50.00 57.31 68.42 49.30 32.21 22.70 55.41
Zhou_XJU_task2_1 ZhouXJU2025 100 31.84 21.38 62.29 57.06 54.10 60.36 26.08 18.08 46.81 52.20 45.71 60.84 53.88 52.80 55.00 62.00 62.00 62.00 52.02 45.00 61.64 49.37 48.63 50.14
Zhou_XJU_task2_2 ZhouXJU2025 94 32.75 21.43 69.44 57.30 55.52 59.19 31.47 21.38 59.57 49.53 41.75 60.87 52.27 50.37 54.31 60.93 60.98 60.88 51.59 44.75 60.91 50.27 49.23 51.36
Zhou_XJU_task2_3 ZhouXJU2025 96 35.96 24.44 68.09 52.62 48.86 57.00 27.14 18.11 54.11 54.70 49.26 61.50 53.70 51.93 55.61 58.92 58.98 58.86 49.26 42.25 59.08 52.99 52.98 53.00
Zhou_XJU_task2_4 ZhouXJU2025 93 28.65 18.15 68.06 54.38 51.43 57.69 34.63 24.37 59.82 58.48 54.10 63.64 51.58 49.81 53.48 58.70 58.85 58.55 49.70 43.93 57.21 54.00 54.00 54.00
Cai_NCUT_task2_1 CaiNCUT2025 45 79.90 80.78 79.05 25.39 16.88 51.23 39.39 30.21 56.59 29.83 21.27 49.89 38.43 28.89 57.40 69.89 67.94 71.95 62.37 60.34 64.55 27.27 17.14 66.67
Cai_NCUT_task2_2 CaiNCUT2025 83 68.36 96.91 52.81 60.27 68.62 53.74 61.10 71.79 53.17 63.15 76.15 53.95 64.01 83.58 51.86 67.12 98.99 50.77 56.52 68.42 48.15 26.72 17.06 61.57
Cai_NCUT_task2_3 CaiNCUT2025 42 68.43 63.55 74.11 50.77 47.08 55.09 35.00 24.44 61.65 55.29 54.84 55.75 53.30 48.07 59.80 75.28 73.42 77.24 52.10 42.93 66.26 54.58 54.84 54.32
Saengthong_SCITOK_task2_1 SaengthongSCITOK2025 84 70.42 82.29 61.54 45.23 35.04 63.79 51.04 43.75 61.24 51.28 45.94 58.03 58.89 51.33 69.06 66.65 97.96 50.51 62.85 75.34 53.91 45.12 38.96 53.59
Saengthong_SCITOK_task2_2 SaengthongSCITOK2025 2 80.32 76.68 84.32 42.25 29.76 72.81 47.48 38.18 62.78 28.11 19.09 53.30 56.48 46.47 71.98 69.92 97.96 54.36 64.37 74.08 56.91 42.21 35.10 52.94
Saengthong_SCITOK_task2_3 SaengthongSCITOK2025 56 69.82 96.99 54.54 64.03 80.89 52.98 59.06 73.42 49.40 44.84 37.50 55.76 66.67 100.00 50.00 69.44 100.00 53.19 62.46 60.42 64.64 60.51 71.94 52.22
Saengthong_SCITOK_task2_4 SaengthongSCITOK2025 80 65.00 78.20 55.62 52.11 44.21 63.44 57.14 61.11 53.66 59.14 61.11 57.29 66.81 69.09 64.69 67.61 83.81 56.66 58.99 66.22 53.19 38.49 28.89 57.65
Zhang_DKU_task2_1 ZhangDKU2025 88 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Zhang_DKU_task2_2 ZhangDKU2025 70 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Zhang_DKU_task2_3 ZhangDKU2025 92 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Zhang_DKU_task2_4 ZhangDKU2025 63 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
WT_IACAS_task2_1 WTIACAS2025 66 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
WT_IACAS_task2_2 WTIACAS2025 44 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
WT_IACAS_task2_3 WTIACAS2025 86 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
WT_IACAS_task2_4 WTIACAS2025 76 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Zhou_XAUAT_task2_1 ZhouXAUAT2025 24 82.05 84.71 79.56 54.81 55.36 54.27 55.75 62.60 50.24 57.69 60.00 55.56 65.82 78.00 56.93 63.10 75.95 53.96 62.51 73.78 54.22 56.57 68.44 48.20
Zhou_XAUAT_task2_2 ZhouXAUAT2025 43 81.84 87.27 77.05 56.67 58.58 54.87 56.66 64.48 50.52 61.09 65.94 56.90 66.12 80.00 56.34 61.25 72.99 52.76 61.93 74.88 52.79 55.19 63.01 49.09
Zhou_XAUAT_task2_3 ZhouXAUAT2025 95 74.46 92.47 62.32 61.75 73.42 53.29 60.16 74.00 50.68 58.84 67.20 52.34 62.64 79.61 51.63 55.58 68.87 46.59 62.45 78.22 51.97 62.14 79.61 50.95
Zhou_XAUAT_task2_4 ZhouXAUAT2025 50 84.01 87.59 80.71 62.00 76.54 52.10 68.29 78.99 60.15 57.30 58.98 55.72 67.06 88.45 54.00 61.80 72.00 54.14 62.48 80.78 50.94 59.43 77.43 48.22
Zhong_USTC_task2_1 ZhongUSTC2025 54 51.94 51.92 51.96 55.01 54.98 55.04 46.96 46.98 46.94 52.78 52.53 53.03 56.97 56.98 56.96 54.90 54.84 54.96 53.91 53.93 53.89 51.49 51.69 51.30
Zhong_USTC_task2_2 ZhongUSTC2025 51 51.94 51.92 51.96 55.01 54.98 55.04 46.96 46.98 46.94 52.78 52.53 53.03 56.97 56.98 56.96 54.90 54.84 54.96 53.91 53.93 53.89 51.49 51.69 51.30
Zhong_USTC_task2_3 ZhongUSTC2025 38 51.94 51.92 51.96 55.01 54.98 55.04 46.96 46.98 46.94 52.78 52.53 53.03 56.97 56.98 56.96 54.90 54.84 54.96 53.91 53.93 53.89 51.49 51.69 51.30
Zhong_USTC_task2_4 ZhongUSTC2025 30 51.94 51.92 51.96 55.01 54.98 55.04 46.96 46.98 46.94 52.78 52.53 53.03 56.97 56.98 56.96 54.90 54.84 54.96 53.91 53.93 53.89 51.49 51.69 51.30
Vijayyan_SNUC_task2_1 VijayyanSNUC2025 109 70.88 82.02 62.40 52.53 48.41 57.42 36.52 31.84 42.81 49.20 49.65 48.75 50.07 45.77 55.27 69.36 94.99 54.62 62.46 70.13 56.30 33.33 25.55 47.94
CHUNG_KUCAU_task2_1 CHUNGKUCAU2025 97 64.64 71.35 59.09 44.90 36.07 59.46 21.30 14.48 40.32 54.52 54.12 54.92 34.74 25.55 54.25 53.39 37.74 91.20 56.91 55.76 58.12 39.34 32.74 49.27
CHUNG_KUCAU_task2_2 CHUNGKUCAU2025 65 49.53 34.60 87.12 48.07 41.74 56.67 44.17 35.80 57.64 51.84 42.35 66.79 42.29 34.91 53.63 25.89 17.78 47.62 56.37 53.77 59.23 25.95 19.20 40.00
CHUNG_KUCAU_task2_3 CHUNGKUCAU2025 72 63.98 58.80 70.17 50.13 43.75 58.68 0.00 0.00 0.00 59.55 61.33 57.86 31.94 21.76 60.04 38.71 24.00 100.00 0.00 0.00 0.00 38.97 30.91 52.71
CHUNG_KUCAU_task2_4 CHUNGKUCAU2025 47 48.92 33.92 87.72 42.98 30.71 71.58 48.73 38.40 66.67 58.06 48.00 73.47 38.43 27.00 66.67 67.86 72.65 63.67 57.12 58.23 56.04 25.44 17.78 44.69
Dung_CNTT1PTIT_task2_1 DungCNTT1PTIT2025 112 64.40 94.99 48.72 46.78 42.79 51.60 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Zhang_NWPU_task2_1 ZhangNWPU2025 103 27.51 17.62 62.71 41.93 38.97 45.37 51.12 47.67 55.11 44.11 40.98 47.75 43.95 40.78 47.66 47.96 44.44 52.08 48.34 44.98 52.25 42.98 39.02 47.82
Zhang_NWPU_task2_2 ZhangNWPU2025 67 58.76 49.35 72.58 46.85 45.91 47.83 53.06 52.00 54.17 49.94 48.82 51.11 52.87 51.69 54.11 51.42 50.04 52.88 52.01 50.98 53.08 51.02 50.00 52.08
Zhang_NWPU_task2_3 ZhangNWPU2025 75 53.76 42.93 71.88 45.91 44.98 46.87 52.96 51.92 54.04 48.96 47.92 50.04 53.00 51.92 54.13 52.66 51.31 54.10 51.02 50.00 52.08 48.98 47.92 50.09
Zhang_NWPU_task2_4 ZhangNWPU2025 82 51.56 40.34 71.43 47.42 46.00 48.94 53.49 51.92 55.15 48.41 46.98 49.93 53.33 51.69 55.08 52.28 50.51 54.19 49.48 48.00 51.06 47.32 45.65 49.11
Chao_BUCT_task2_1 ChaoBUCT2025 118 53.45 53.33 53.57 39.73 33.92 47.94 61.54 61.74 61.35 52.82 48.44 58.06 55.67 55.71 55.63 38.00 38.00 38.00 48.92 48.98 48.86 43.35 39.32 48.30
Chao_BUCT_task2_2 ChaoBUCT2025 114 66.67 100.00 50.00 31.14 22.06 52.91 66.67 100.00 50.00 66.67 100.00 50.00 48.83 48.72 48.94 67.62 89.82 54.22 66.67 100.00 50.00 66.67 100.00 50.00
Chao_BUCT_task2_3 ChaoBUCT2025 108 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
Li_XJTLU_task2_1 LiXJTLU2025 89 69.14 68.64 69.65 47.95 47.67 48.23 32.62 24.00 50.91 55.05 51.43 59.21 56.61 56.56 56.66 49.85 49.41 50.30 46.97 41.21 54.60 52.73 52.15 53.33
Li_XJTLU_task2_2 LiXJTLU2025 87 69.14 68.64 69.65 55.00 54.98 55.02 32.62 24.00 50.91 46.06 44.88 47.30 51.84 48.44 55.76 49.85 49.41 50.30 46.97 41.21 54.60 53.73 51.43 56.25
Li_XJTLU_task2_3 LiXJTLU2025 106 60.34 60.20 60.47 43.51 38.20 50.54 44.86 37.53 55.75 50.04 49.92 50.16 53.27 50.37 56.53 48.74 48.49 48.99 57.53 55.19 60.07 49.00 48.98 49.02
Li_XJTLU_task2_4 LiXJTLU2025 99 61.03 56.77 65.97 46.10 37.53 59.76 39.11 33.70 46.59 45.10 43.83 46.45 52.86 52.83 52.89 68.69 68.64 68.74 56.00 53.05 59.29 52.70 52.08 53.34
Wang_ZJU_task2_1 WangZJU2025 107 0.00 0.00 0.00 20.78 12.80 55.17 25.19 18.18 40.98 21.12 12.80 60.38 22.73 13.75 65.48 0.00 0.00 0.00 7.00 3.80 44.19 0.00 0.00 0.00
Wang_ZJU_task2_2 WangZJU2025 64 66.67 100.00 50.00 62.05 75.00 52.91 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Wang_ZJU_task2_3 WangZJU2025 85 71.00 90.11 58.57 59.65 68.62 52.76 59.98 68.42 53.39 62.16 77.47 51.91 64.62 84.84 52.19 0.00 0.00 0.00 55.87 66.67 48.08 56.90 53.43 60.86
Wang_ZJU_task2_4 WangZJU2025 55 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Lin_IASP_task2_1 LinIASP2025 105 78.39 76.88 79.96 46.36 40.63 53.99 45.36 42.79 48.27 44.97 40.78 50.12 28.03 19.83 47.79 41.71 37.89 46.39 41.27 33.22 54.46 53.78 55.93 51.79
Lin_IASP_task2_2 LinIASP2025 78 77.87 77.95 77.79 53.35 52.08 54.70 52.36 46.34 60.16 53.97 52.15 55.92 53.42 49.26 58.35 54.60 54.55 54.64 46.89 43.92 50.29 58.99 58.98 59.00
Lin_IASP_task2_3 LinIASP2025 74 75.58 77.97 73.33 40.14 34.69 47.62 52.51 52.94 52.08 48.31 45.04 52.10 58.32 54.62 62.56 55.32 49.92 62.03 35.24 25.26 58.25 61.45 62.86 60.11
Lin_IASP_task2_4 LinIASP2025 73 64.35 64.48 64.23 52.48 51.31 53.70 54.98 54.11 55.88 47.37 47.67 47.08 51.67 50.72 52.66 56.96 56.84 57.08 50.85 50.08 51.65 54.32 54.11 54.53
Lobanov_ITMO_task2_1 LobanovITMO2025 110 69.89 96.91 54.65 45.98 41.62 51.35 40.00 32.00 53.33 36.59 30.00 46.88 41.82 36.28 49.37 19.44 12.92 39.25 34.55 31.06 38.94 35.49 25.20 60.00
Lobanov_ITMO_task2_2 LobanovITMO2025 98 68.53 98.99 52.41 44.89 37.89 55.05 32.17 25.71 42.96 23.17 14.12 64.52 34.63 27.87 45.73 28.07 19.20 52.17 32.60 25.87 44.04 43.62 38.57 50.19
Qian_nivic_task2_1 Qiannivic2025 32 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Qian_nivic_task2_2 Qiannivic2025 28 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Qian_nivic_task2_3 Qiannivic2025 49 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Qian_nivic_task2_4 Qiannivic2025 39 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Wang_MYPS_task2_1 WangMYPS2025 16 74.16 71.35 77.19 57.68 57.72 57.64 57.92 56.95 58.93 47.09 46.98 47.20 58.00 58.00 58.00 87.06 86.71 87.42 56.48 55.19 57.83 48.94 48.49 49.40
Wang_MYPS_task2_2 WangMYPS2025 20 76.63 76.15 77.10 57.68 57.72 57.64 57.92 56.95 58.93 47.09 46.98 47.20 59.73 59.73 59.73 86.13 85.81 86.46 56.48 55.19 57.83 48.94 48.49 49.40
Wang_MYPS_task2_3 WangMYPS2025 1 73.43 71.89 75.04 59.46 59.40 59.52 52.00 51.47 52.54 59.97 59.93 60.01 61.98 61.74 62.22 83.02 82.99 83.05 59.02 58.33 59.73 44.00 43.64 44.36
Wang_MYPS_task2_4 WangMYPS2025 4 71.69 67.83 76.02 59.46 59.40 59.52 52.00 51.47 52.54 59.97 59.93 60.01 64.83 64.86 64.80 82.05 81.95 82.15 59.02 58.33 59.73 44.00 43.64 44.36
Emon_HDK_task2_1 EmonHDK2025 121 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 6.81 3.69 43.64 10.70 6.40 32.65 13.95 8.40 41.18 0.00 0.00 0.00 11.91 6.77 49.44
Fu_CUMT_task2_1 FuCUMT2025 52 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Fu_CUMT_task2_2 FuCUMT2025 40 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Fu_CUMT_task2_3 FuCUMT2025 41 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Fu_CUMT_task2_4 FuCUMT2025 26 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Ding_HFUU_task2_1 DingHFUU2025 71 68.97 100.00 52.63 63.16 79.52 52.38 60.18 79.52 48.41 64.05 92.73 48.92 62.57 83.58 50.00 0.00 0.00 0.00 62.40 87.64 48.45 0.00 0.00 0.00
Ding_HFUU_task2_2 DingHFUU2025 81 63.89 63.01 64.79 0.00 0.00 0.00 49.26 46.15 52.82 64.98 94.74 49.45 64.66 92.47 49.71 0.00 0.00 0.00 0.00 0.00 0.00 57.32 60.88 54.16
Ding_HFUU_task2_3 DingHFUU2025 91 41.85 32.98 57.25 60.06 70.68 52.22 57.46 64.86 51.57 64.09 80.96 53.03 61.41 78.22 50.55 64.98 90.00 50.85 56.18 66.67 48.54 29.34 20.00 55.05
Ding_HFUU_task2_4 DingHFUU2025 59 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Yang_NBU_task2_1 YangNBU2025 3 51.92 51.92 51.92 47.61 47.25 47.97 51.85 51.69 52.01 44.05 43.91 44.19 53.01 52.98 53.04 49.92 49.92 49.92 42.00 42.00 42.00 52.89 52.83 52.95
Yang_NBU_task2_2 YangNBU2025 6 51.92 51.92 51.92 47.61 47.25 47.97 51.85 51.69 52.01 44.05 43.91 44.19 53.01 52.98 53.04 49.92 49.92 49.92 42.00 42.00 42.00 52.89 52.83 52.95
Yang_NBU_task2_3 YangNBU2025 5 51.92 51.92 51.92 47.61 47.25 47.97 51.85 51.69 52.01 44.05 43.91 44.19 53.01 52.98 53.04 49.92 49.92 49.92 42.00 42.00 42.00 52.89 52.83 52.95
Yang_NBU_task2_4 YangNBU2025 8 51.92 51.92 51.92 47.61 47.25 47.97 51.85 51.69 52.01 44.05 43.91 44.19 53.01 52.98 53.04 49.92 49.92 49.92 42.00 42.00 42.00 52.89 52.83 52.95
Kret_CU_task2_1 KretCU2025 115 0.00 0.00 0.00 6.79 3.69 42.11 41.83 36.98 48.15 57.10 61.11 53.58 24.62 15.65 57.69 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
Zheng_SJTU-AITHU_task2_1 ZhengSJTU-AITHU2025 13 81.01 80.89 81.13 63.95 63.75 64.15 46.54 45.55 47.57 59.00 58.98 59.02 56.03 55.71 56.36 61.94 61.94 61.94 56.07 54.88 57.31 45.93 43.92 48.13
Zheng_SJTU-AITHU_task2_2 ZhengSJTU-AITHU2025 11 85.81 85.26 86.38 64.07 63.75 64.39 48.81 47.69 49.98 56.05 55.93 56.17 57.37 56.90 57.85 61.96 61.94 61.98 56.81 55.52 58.16 45.88 42.67 49.61
Zheng_SJTU-AITHU_task2_3 ZhengSJTU-AITHU2025 15 85.81 85.26 86.38 66.06 65.45 66.67 47.27 46.08 48.53 56.00 56.00 56.00 56.02 55.58 56.47 60.89 60.59 61.19 54.26 52.50 56.15 45.09 39.00 53.42
Zheng_SJTU-AITHU_task2_4 ZhengSJTU-AITHU2025 12 85.81 85.26 86.38 64.07 63.75 64.39 48.81 47.69 49.98 56.05 55.93 56.17 56.11 55.58 56.65 62.99 62.98 63.00 56.81 55.52 58.16 45.52 41.63 50.20
Zhao_CUMT_task2_1 ZhaoCUMT2025 102 68.86 96.91 53.41 20.92 13.22 50.17 17.33 11.16 38.71 22.16 13.33 65.57 32.73 24.00 51.43 0.00 0.00 0.00 42.91 41.48 44.44 0.00 0.00 0.00
Zhao_CUMT_task2_2 ZhaoCUMT2025 101 68.86 96.91 53.41 20.92 13.22 50.17 17.33 11.16 38.71 22.16 13.33 65.57 32.73 24.00 51.43 0.00 0.00 0.00 42.91 41.48 44.44 0.00 0.00 0.00
Zhao_CUMT_task2_3 ZhaoCUMT2025 61 61.50 60.85 62.16 20.92 13.22 50.17 17.33 11.16 38.71 22.16 13.33 65.57 32.73 24.00 51.43 0.00 0.00 0.00 42.91 41.48 44.44 0.00 0.00 0.00
Zhao_CUMT_task2_4 ZhaoCUMT2025 62 61.50 60.85 62.16 20.92 13.22 50.17 17.33 11.16 38.71 22.16 13.33 65.57 32.73 24.00 51.43 0.00 0.00 0.00 42.91 41.48 44.44 0.00 0.00 0.00
Ozeki_MELCO_task2_1 OzekiMELCO2025 23 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Ozeki_MELCO_task2_2 OzekiMELCO2025 60 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Ozeki_MELCO_task2_3 OzekiMELCO2025 69 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Ozeki_MELCO_task2_4 OzekiMELCO2025 79 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Huang_XJU_task2_1 HuangXJU2025 25 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Huang_XJU_task2_2 HuangXJU2025 27 66.67 100.00 50.00 66.67 100.00 50.00 70.59 76.80 65.31 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Huang_XJU_task2_3 HuangXJU2025 35 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Huang_XJU_task2_4 HuangXJU2025 37 66.67 100.00 50.00 66.67 100.00 50.00 23.79 14.44 67.36 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Fujimura_NU_task2_1 FujimuraNU2025 7 66.89 100.00 50.25 68.19 75.95 61.86 0.00 0.00 0.00 48.60 38.77 65.12 5.19 2.67 100.00 66.67 100.00 50.00 62.57 70.74 56.09 66.67 100.00 50.00
Fujimura_NU_task2_2 FujimuraNU2025 21 66.67 100.00 50.00 68.65 92.90 54.44 0.00 0.00 0.00 63.88 67.83 60.37 63.32 87.27 49.69 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Fujimura_NU_task2_3 FujimuraNU2025 14 67.34 100.00 50.76 68.09 96.00 52.75 13.41 7.47 65.88 65.60 79.80 55.69 58.78 61.77 56.07 66.67 100.00 50.00 65.45 86.36 52.69 66.67 100.00 50.00
Fujimura_NU_task2_4 FujimuraNU2025 9 67.34 100.00 50.76 67.62 92.99 53.13 13.57 7.53 68.82 66.89 87.95 53.97 46.46 33.95 73.57 66.67 100.00 50.00 62.07 71.27 54.98 66.67 100.00 50.00
Jiang_THUEE_task2_1 JiangTHUEE2025 19 86.86 86.44 87.28 64.10 63.44 64.77 48.81 47.69 49.98 56.07 55.93 56.21 54.39 54.11 54.67 62.95 62.86 63.04 54.40 52.50 56.45 43.97 38.48 51.28
Jiang_THUEE_task2_2 JiangTHUEE2025 10 88.81 88.09 89.54 64.15 63.75 64.56 50.81 49.81 51.85 55.02 54.98 55.06 57.53 56.90 58.18 65.72 65.76 65.68 58.14 56.95 59.38 46.35 43.92 49.07
Jiang_THUEE_task2_3 JiangTHUEE2025 18 86.61 86.07 87.15 63.21 62.60 63.82 50.27 49.23 51.36 56.95 56.98 56.92 56.63 56.14 57.12 64.96 64.98 64.94 55.82 54.04 57.72 43.51 38.20 50.54
Jiang_THUEE_task2_4 JiangTHUEE2025 17 88.63 87.64 89.63 63.13 62.22 64.07 48.93 47.69 50.25 56.95 56.98 56.92 55.49 54.86 56.14 62.00 62.00 62.00 54.96 53.43 56.58 46.26 42.00 51.47
Bian_TGU_task2_1 BianTGU2025 119 0.00 0.00 0.00 0.00 0.00 0.00 9.04 5.33 29.63 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 15.62 10.00 35.71
Bian_TGU_task2_2 BianTGU2025 116 13.26 8.00 38.71 33.03 24.30 51.56 18.15 10.91 54.05 14.68 8.73 46.15 14.04 8.00 57.14 12.60 6.86 77.42 6.15 3.33 40.00 14.65 8.89 41.67
Bian_TGU_task2_3 BianTGU2025 104 16.27 9.60 53.33 24.95 15.75 60.00 14.76 8.40 60.87 31.33 22.61 50.98 0.00 0.00 0.00 25.51 15.75 67.02 20.33 12.31 58.39 0.00 0.00 0.00
Bian_TGU_task2_4 BianTGU2025 120 17.10 10.18 53.33 0.00 0.00 0.00 17.69 11.73 35.92 36.35 28.97 48.78 0.00 0.00 0.00 17.14 10.91 40.00 0.00 0.00 0.00 16.67 10.67 38.10
Sera_TMU_task2_1 SeraTMU2025 57 0.00 0.00 0.00 7.17 3.75 81.08 0.00 0.00 0.00 20.00 12.00 60.00 7.01 3.69 68.57 32.79 20.00 90.91 0.00 0.00 0.00 18.43 10.91 59.41
Kim_DAU_task2_1 KimDAU2025 113 38.89 37.33 40.58 15.65 9.00 60.00 60.80 66.34 56.11 60.16 70.99 52.20 59.12 80.99 46.55 58.25 74.35 47.89 56.44 61.94 51.84 27.04 19.20 45.71
Kim_DAU_task2_2 KimDAU2025 111 48.79 45.96 52.00 16.34 9.75 50.32 54.26 62.40 48.00 58.03 73.42 47.97 55.43 60.98 50.81 19.29 12.92 38.01 28.39 19.80 50.13 25.63 18.20 43.33
Wang_UniS_task2_1 WangUniS2025 34 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Wang_UniS_task2_2 WangUniS2025 46 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Wang_UniS_task2_3 WangUniS2025 53 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Wang_UniS_task2_4 WangUniS2025 90 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00
Guan_HEU_task2_1 GuanHEU2025 22 60.06 54.19 67.36 29.70 19.35 63.83 40.13 30.41 58.96 27.05 18.67 49.12 33.04 22.40 62.92 63.91 47.35 98.31 40.52 28.10 72.64 32.35 21.82 62.50
Guan_HEU_task2_2 GuanHEU2025 48 66.67 76.72 58.94 29.70 19.35 63.83 42.75 33.22 59.94 25.81 17.45 49.48 33.27 22.56 63.34 69.12 54.04 95.89 31.52 19.50 82.11 31.05 20.95 59.95
Guan_HEU_task2_3 GuanHEU2025 117 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 6.43 3.33 90.91 0.00 0.00 0.00 10.75 5.71 90.91 6.94 3.75 46.88 8.92 4.80 63.16
Guan_HEU_task2_4 GuanHEU2025 68 63.95 61.61 66.47 7.21 3.79 75.00 23.97 14.75 64.05 30.03 20.36 57.14 35.65 25.60 58.72 63.05 47.25 94.74 43.48 31.84 68.54 14.51 8.40 53.16
Kim_AISTAT_task2_1 KimAISTAT2025 31 79.25 84.00 75.00 26.93 17.73 56.03 23.74 14.72 61.33 65.74 60.59 71.85 34.86 27.47 47.67 66.89 100.00 50.25 68.47 97.96 52.63 52.76 56.84 49.23
Kim_AISTAT_task2_2 KimAISTAT2025 33 79.37 80.99 77.82 26.89 17.73 55.63 23.62 14.67 60.69 65.20 59.40 72.26 35.20 27.47 48.97 66.89 100.00 50.25 68.71 97.96 52.91 52.42 55.93 49.32
Kim_AISTAT_task2_3 KimAISTAT2025 36 82.21 82.99 81.44 30.59 20.80 57.78 23.68 14.72 60.53 65.66 61.42 70.52 37.08 29.74 49.24 66.89 100.00 50.25 68.53 96.99 52.98 53.52 56.84 50.56
Kim_AISTAT_task2_4 KimAISTAT2025 29 79.88 85.95 74.61 37.03 26.55 61.18 23.80 14.75 61.64 66.81 62.60 71.63 37.38 30.00 49.59 66.89 100.00 50.25 68.24 97.96 52.36 53.17 58.58 48.68


Domain-wise performance

Rank Submission Information Ranking Eveluation Dataset in Source Domain Eveluation Dataset in Target Domain
Submission Code Technical
Report
Official
Rank
Official
Score
Harmonic mean
(AUC, source)
AutoTrash
(AUC, source)
AutoTrash
(pAUC, source)
BandSealer
(AUC, source)
BandSealer
(pAUC, source)
CoffeeGrinder
(AUC, source)
CoffeeGrinder
(pAUC, source)
HomeCamera
(AUC, source)
HomeCamera
(pAUC, source)
Polisher
(AUC, source)
Polisher
(pAUC, source)
ScrewFeeder
(AUC, source)
ScrewFeeder
(pAUC, source)
ToyPet
(AUC, source)
ToyPet
(pAUC, source)
ToyRCCar
(AUC, source)
ToyRCCar
(pAUC, source)
Harmonic mean
(AUC, target)
AutoTrash
(AUC, target)
AutoTrash
(pAUC, target)
BandSealer
(AUC, target)
BandSealer
(pAUC, target)
CoffeeGrinder
(AUC, target)
CoffeeGrinder
(pAUC, target)
HomeCamera
(AUC, target)
HomeCamera
(pAUC, target)
Polisher
(AUC, target)
Polisher
(pAUC, target)
ScrewFeeder
(AUC, target)
ScrewFeeder
(pAUC, target)
ToyPet
(AUC, target)
ToyPet
(pAUC, target)
ToyRCCar
(AUC, target)
ToyRCCar
(pAUC, target)
DCASE2025_baseline_task2_MAHALA DCASE2025baseline2025 58 56.506 71.99 77.26 54.16 76.38 49.11 74.98 51.42 86.16 51.84 70.42 53.79 72.90 70.05 69.82 56.84 55.86 54.00 47.88 52.60 54.16 32.68 49.11 40.42 51.42 42.64 51.84 52.78 53.79 79.04 70.05 50.90 56.84 55.48 54.00
DCASE2025_baseline_task2_MSE DCASE2025baseline2025 77 54.428 68.80 81.02 54.21 71.98 52.05 73.04 53.42 81.40 52.84 66.86 52.32 64.86 62.11 67.70 55.00 52.84 55.53 44.95 34.36 54.21 39.56 52.05 44.36 53.42 49.76 52.84 44.30 52.32 65.92 62.11 36.70 55.00 62.72 55.53
Zhou_XJU_task2_1 ZhouXJU2025 100 52.417 67.81 85.56 49.53 68.76 50.89 70.26 50.16 77.56 52.84 64.56 51.42 61.14 59.11 74.90 54.32 51.50 53.32 42.63 31.94 49.53 45.18 50.89 31.00 50.16 35.62 52.84 47.08 51.42 73.64 59.11 44.90 54.32 59.54 53.32
Zhou_XJU_task2_2 ZhouXJU2025 94 52.848 67.52 86.70 49.53 68.78 51.89 72.82 50.68 77.60 52.95 64.58 51.47 57.92 57.37 75.84 53.79 50.36 53.42 43.62 30.74 49.53 49.60 51.89 34.76 50.68 35.70 52.95 46.24 51.47 72.80 57.37 44.72 53.79 61.70 53.42
Zhou_XJU_task2_3 ZhouXJU2025 96 52.631 68.73 86.58 51.05 69.86 50.47 71.64 51.26 79.10 54.11 64.88 51.05 57.70 59.74 74.34 53.58 56.36 53.74 42.42 30.46 51.05 44.52 50.47 31.20 51.26 39.80 54.11 46.00 51.05 72.50 59.74 43.64 53.58 56.52 53.74
Zhou_XJU_task2_4 ZhouXJU2025 93 52.907 68.55 87.88 51.11 71.04 52.32 73.38 52.16 80.80 53.74 64.60 50.58 57.92 57.11 75.16 53.42 52.10 52.00 43.19 29.30 51.11 46.58 52.32 33.90 52.16 42.48 53.74 45.54 50.58 71.50 57.11 43.08 53.42 57.38 52.00
Cai_NCUT_task2_1 CaiNCUT2025 45 57.344 74.44 92.46 66.26 66.24 56.26 76.52 52.47 69.62 50.05 74.00 50.21 80.28 63.84 83.06 58.21 62.04 53.05 47.75 78.86 66.26 47.74 56.26 31.42 52.47 39.12 50.05 45.96 50.21 79.28 63.84 46.02 58.21 48.96 53.05
Cai_NCUT_task2_2 CaiNCUT2025 83 54.058 67.83 85.12 53.68 70.72 52.63 73.38 52.79 74.32 53.42 67.20 51.11 63.08 58.42 66.90 54.74 51.86 56.32 44.94 35.66 53.68 42.76 52.63 43.70 52.79 43.54 53.42 45.26 51.11 64.04 58.42 36.18 54.74 64.92 56.32
Cai_NCUT_task2_3 CaiNCUT2025 42 57.559 74.16 92.43 61.29 69.14 54.89 75.59 52.63 68.36 50.26 75.29 51.24 81.64 67.08 81.55 58.13 59.03 52.50 48.49 64.44 61.29 49.83 54.89 32.89 52.63 37.61 50.26 44.03 51.24 85.24 67.08 47.01 58.13 59.90 52.50
Saengthong_SCITOK_task2_1 SaengthongSCITOK2025 84 53.815 79.57 91.64 54.68 76.98 54.21 84.64 50.89 78.66 50.26 84.50 53.00 78.02 67.32 82.14 58.00 65.44 52.74 40.15 41.26 54.68 38.58 54.21 31.14 50.89 25.32 50.26 49.48 53.00 79.60 67.32 44.00 58.00 45.52 52.74
Saengthong_SCITOK_task2_2 SaengthongSCITOK2025 2 61.569 69.52 87.56 71.05 63.32 57.37 78.36 52.00 47.82 52.32 78.92 56.68 79.94 73.47 79.32 57.84 61.00 51.63 58.40 84.62 71.05 61.46 57.37 40.30 52.00 57.88 52.32 58.82 56.68 89.08 73.47 58.16 57.84 46.78 51.63
Saengthong_SCITOK_task2_3 SaengthongSCITOK2025 56 56.636 72.99 82.60 58.11 70.24 55.74 74.92 50.42 65.32 50.21 77.08 49.16 89.16 81.63 75.44 57.68 58.30 52.89 46.94 65.58 58.11 50.30 55.74 32.30 50.42 38.10 50.21 29.52 49.16 93.46 81.63 59.58 57.68 59.78 52.89
Saengthong_SCITOK_task2_4 SaengthongSCITOK2025 80 54.326 75.62 80.68 50.89 75.36 52.79 78.70 50.42 81.50 50.05 80.34 56.00 71.68 61.89 76.52 59.16 63.74 52.32 42.66 38.18 50.89 42.66 52.79 32.32 50.42 31.54 50.05 55.76 56.00 72.98 61.89 45.98 59.16 45.70 52.32
Zhang_DKU_task2_1 ZhangDKU2025 88 53.462 47.34 58.78 60.11 61.70 54.58 53.74 51.84 29.04 52.05 51.54 51.05 60.24 54.05 49.10 52.11 37.94 50.84 61.77 80.68 60.11 44.74 54.58 63.94 51.84 70.22 52.05 55.22 51.05 68.56 54.05 57.86 52.11 67.04 50.84
Zhang_DKU_task2_2 ZhangDKU2025 70 55.184 53.60 78.42 67.21 38.04 51.00 52.84 50.58 56.68 52.00 54.58 53.58 53.04 54.00 53.54 53.11 56.20 50.21 58.72 90.00 67.21 67.36 51.00 61.08 50.58 39.62 52.00 59.26 53.58 68.96 54.00 55.64 53.11 51.76 50.21
Zhang_DKU_task2_3 ZhangDKU2025 92 52.980 52.83 68.74 57.21 54.80 52.11 35.16 48.84 42.88 54.63 53.86 56.53 57.22 56.47 59.96 50.05 70.70 49.53 53.13 84.82 57.21 57.12 52.11 51.72 48.84 64.72 54.63 65.78 56.53 67.18 56.47 46.20 50.05 28.78 49.53
Zhang_DKU_task2_4 ZhangDKU2025 63 55.762 53.01 80.08 65.21 50.46 51.84 52.34 51.74 35.96 55.32 53.50 54.21 62.32 56.42 56.60 52.26 51.82 50.79 60.40 86.06 65.21 64.16 51.84 58.90 51.74 62.90 55.32 64.60 54.21 75.28 56.42 48.54 52.26 43.46 50.79
WT_IACAS_task2_1 WTIACAS2025 66 55.534 79.46 95.30 67.26 84.20 58.58 84.06 53.11 87.38 52.95 84.04 57.16 55.74 56.53 86.16 53.95 73.92 50.84 42.45 68.40 67.26 52.54 58.58 37.42 53.11 35.90 52.95 42.36 57.16 62.80 56.53 40.82 53.95 27.64 50.84
WT_IACAS_task2_2 WTIACAS2025 44 57.441 78.79 93.48 72.74 75.68 61.37 84.28 51.63 84.64 52.89 84.82 56.63 62.32 62.84 85.80 55.00 69.18 51.21 45.28 81.84 72.74 59.86 61.37 35.66 51.63 35.84 52.89 43.82 56.63 71.24 62.84 45.14 55.00 30.48 51.21
WT_IACAS_task2_3 WTIACAS2025 86 53.521 78.33 96.82 64.84 86.30 57.74 84.90 51.95 87.08 52.79 83.28 55.21 49.72 53.26 86.44 54.63 75.36 50.89 39.90 54.72 64.84 46.68 57.74 35.54 51.95 35.54 52.79 38.54 55.21 55.18 53.26 39.10 54.63 28.66 50.89
WT_IACAS_task2_4 WTIACAS2025 76 54.440 77.45 95.96 66.32 83.84 58.89 84.90 51.63 85.84 53.16 83.66 54.26 49.64 55.53 85.92 56.42 72.60 52.32 41.23 58.56 66.32 47.36 58.89 34.12 51.63 35.38 53.16 38.78 54.26 57.96 55.53 42.52 56.42 31.52 52.32
Zhou_XAUAT_task2_1 ZhouXAUAT2025 24 58.188 56.49 89.52 79.16 59.14 50.63 55.90 51.84 65.24 55.32 62.22 54.05 38.82 51.42 60.22 53.58 45.68 54.79 63.38 91.66 79.16 52.50 50.63 54.40 51.84 59.12 55.32 63.26 54.05 81.14 51.42 63.58 53.58 58.48 54.79
Zhou_XAUAT_task2_2 ZhouXAUAT2025 43 57.510 54.30 90.44 79.68 55.88 50.21 58.24 52.89 66.26 54.63 55.86 53.63 36.82 51.21 59.70 54.63 41.14 53.63 63.90 90.62 79.68 50.74 50.21 55.52 52.89 61.10 54.63 66.50 53.63 74.66 51.21 57.10 54.63 70.82 53.63
Zhou_XAUAT_task2_3 ZhouXAUAT2025 95 52.663 53.92 96.48 77.00 54.48 50.74 68.84 49.42 72.14 51.16 55.88 53.95 27.00 48.53 55.28 52.47 54.82 53.79 50.61 76.60 77.00 58.98 50.74 27.94 49.42 37.38 51.16 57.84 53.95 63.64 48.53 61.14 52.47 61.84 53.79
Zhou_XAUAT_task2_4 ZhouXAUAT2025 50 57.092 55.87 91.62 81.63 56.88 51.16 84.06 49.84 64.42 56.05 61.10 53.89 37.20 51.05 53.34 51.74 39.56 53.47 60.92 91.58 81.63 58.90 51.16 44.18 49.84 56.32 56.05 67.66 53.89 76.16 51.05 54.34 51.74 59.84 53.47
Zhong_USTC_task2_1 ZhongUSTC2025 54 56.896 55.10 66.48 75.05 63.82 55.21 51.70 50.26 43.74 52.05 60.14 57.42 66.08 58.95 58.96 54.74 42.44 49.32 60.08 94.12 75.05 55.54 55.21 48.34 50.26 56.82 52.05 74.98 57.42 85.36 58.95 60.02 54.74 40.78 49.32
Zhong_USTC_task2_2 ZhongUSTC2025 51 57.068 56.37 75.79 56.10 63.82 55.21 51.70 50.26 43.74 52.05 64.52 62.16 67.48 63.53 58.96 54.74 42.44 49.32 60.05 87.73 56.10 55.54 55.21 48.34 50.26 56.82 52.05 77.80 62.16 87.02 63.53 60.02 54.74 40.78 49.32
Zhong_USTC_task2_3 ZhongUSTC2025 38 57.698 54.18 66.48 75.05 49.26 55.21 58.26 55.68 43.74 52.05 60.14 57.42 66.08 58.95 58.96 54.74 42.44 49.32 63.10 94.12 75.05 64.76 55.21 59.26 55.68 56.82 52.05 74.98 57.42 85.36 58.95 60.02 54.74 40.78 49.32
Zhong_USTC_task2_4 ZhongUSTC2025 30 57.875 55.42 75.79 56.10 49.26 55.21 58.26 55.68 43.74 52.05 64.52 62.16 67.48 63.53 58.96 54.74 42.44 49.32 63.07 87.73 56.10 64.76 55.21 59.26 55.68 56.82 52.05 77.80 62.16 87.02 63.53 60.02 54.74 40.78 49.32
Vijayyan_SNUC_task2_1 VijayyanSNUC2025 109 49.905 70.53 88.26 56.74 75.18 48.32 60.18 50.53 70.76 47.37 68.28 51.32 80.88 63.47 75.66 52.89 56.14 49.89 37.37 50.68 56.74 28.34 48.32 36.84 50.53 22.70 47.37 43.58 51.32 65.94 63.47 38.58 52.89 41.96 49.89
CHUNG_KUCAU_task2_1 CHUNGKUCAU2025 97 52.535 72.92 78.18 53.84 75.34 50.68 64.13 48.32 77.84 50.63 73.38 52.26 73.88 65.63 78.50 51.16 65.32 48.74 41.25 60.92 53.84 31.78 50.68 34.22 48.32 36.22 50.63 44.88 52.26 77.56 65.63 38.18 51.16 35.90 48.74
CHUNG_KUCAU_task2_2 CHUNGKUCAU2025 65 55.554 67.99 79.82 66.42 70.60 53.63 74.68 55.84 84.38 54.26 70.06 51.63 52.02 51.37 78.94 50.16 51.12 48.84 48.46 75.82 66.42 45.90 53.63 43.08 55.84 42.98 54.26 44.24 51.63 65.48 51.37 42.76 50.16 44.74 48.84
CHUNG_KUCAU_task2_3 CHUNGKUCAU2025 72 54.778 74.22 93.80 56.95 76.84 55.16 71.09 49.53 77.42 55.68 67.12 53.68 73.97 68.61 78.60 51.47 62.56 51.32 43.39 49.36 56.95 36.34 55.16 32.96 49.53 45.62 55.68 47.96 53.68 80.50 68.61 38.20 51.47 40.16 51.32
CHUNG_KUCAU_task2_4 CHUNGKUCAU2025 47 57.227 71.09 86.48 67.68 70.38 56.95 78.22 51.16 83.16 57.84 70.54 52.37 76.04 67.32 73.38 47.58 47.64 51.37 49.01 70.18 67.68 64.54 56.95 35.20 51.16 51.42 57.84 46.68 52.37 72.50 67.32 34.84 47.58 46.02 51.37
Dung_CNTT1PTIT_task2_1 DungCNTT1PTIT2025 112 48.719 48.97 44.60 54.58 48.74 48.68 59.92 51.74 53.10 51.05 52.58 50.58 40.46 49.11 43.32 48.68 55.26 52.47 46.58 34.20 54.58 51.46 48.68 49.82 51.74 50.02 51.05 50.70 50.58 46.94 49.11 42.74 48.68 53.84 52.47
Zhang_NWPU_task2_1 ZhangNWPU2025 103 51.635 67.49 94.18 52.42 63.22 55.47 72.86 50.11 50.80 58.00 82.26 56.42 49.86 55.58 79.62 58.74 71.88 48.42 40.29 26.64 52.42 66.00 55.47 41.44 50.11 65.90 58.00 50.86 56.42 70.64 55.58 44.52 58.74 19.88 48.42
Zhang_NWPU_task2_2 ZhangNWPU2025 67 55.425 70.47 94.62 56.95 66.88 55.95 74.26 50.84 56.58 55.11 82.30 58.32 54.14 57.53 79.10 58.32 73.56 47.95 46.05 50.44 56.95 62.24 55.95 39.26 50.84 54.56 55.11 50.62 58.32 73.30 57.53 51.62 58.32 24.24 47.95
Zhang_NWPU_task2_3 ZhangNWPU2025 75 54.536 69.90 95.54 57.68 64.82 54.68 74.56 51.05 54.12 56.00 83.06 59.26 53.62 57.47 79.68 58.42 74.52 47.63 44.40 47.44 57.68 63.60 54.68 39.20 51.05 57.14 56.00 50.68 59.26 73.96 57.47 49.80 58.42 21.26 47.63
Zhang_NWPU_task2_4 ZhangNWPU2025 82 54.279 69.37 95.66 58.58 64.80 55.16 74.28 51.05 53.80 55.63 83.30 58.63 51.60 56.37 80.14 58.53 73.92 47.68 44.15 50.04 58.58 63.48 55.16 38.92 51.05 55.10 55.63 48.78 58.63 65.82 56.37 49.00 58.53 21.96 47.68
Chao_BUCT_task2_1 ChaoBUCT2025 118 47.243 42.02 57.60 52.68 30.46 49.79 77.04 51.47 37.06 49.11 50.40 51.79 26.34 48.58 38.66 49.26 60.44 49.68 50.49 57.22 52.68 67.24 49.79 60.16 51.47 71.68 49.11 60.32 51.79 38.68 48.58 53.76 49.26 28.98 49.68
Chao_BUCT_task2_2 ChaoBUCT2025 114 48.452 47.37 53.89 48.92 59.06 50.69 44.93 48.91 28.30 51.92 53.40 52.39 69.06 51.62 53.05 49.23 42.09 49.65 47.72 53.04 48.92 35.86 50.69 39.80 48.91 56.69 51.92 53.19 52.39 55.78 51.62 49.02 49.23 47.58 49.65
Chao_BUCT_task2_3 ChaoBUCT2025 108 50.132 58.27 62.66 50.26 73.82 48.58 74.90 50.95 57.36 52.11 51.63 51.79 52.31 48.63 65.52 48.47 43.00 49.63 44.08 51.84 50.26 25.04 48.58 66.72 50.95 64.32 52.11 53.98 51.79 34.10 48.63 42.30 48.47 49.40 49.63
Li_XJTLU_task2_1 LiXJTLU2025 89 53.298 64.40 83.48 68.11 56.04 51.53 71.32 52.05 79.82 50.05 60.38 50.95 56.54 50.05 74.02 51.00 49.78 49.79 46.11 70.22 68.11 42.76 51.53 30.28 52.05 42.24 50.05 60.04 50.95 52.32 50.05 41.26 51.00 52.18 49.79
Li_XJTLU_task2_2 LiXJTLU2025 87 53.469 62.69 83.48 68.11 52.94 51.11 71.32 52.05 52.78 53.63 73.18 50.00 56.54 50.05 74.02 51.00 52.88 49.89 47.19 70.22 68.11 51.84 51.11 30.28 52.05 53.80 53.63 41.04 50.00 52.32 50.05 41.26 51.00 60.06 49.89
Li_XJTLU_task2_3 LiXJTLU2025 106 50.876 62.37 66.94 57.74 69.56 51.63 70.64 52.37 52.92 48.37 72.88 49.95 50.30 48.37 73.66 54.42 53.42 50.26 42.54 68.56 57.74 34.74 51.63 36.64 52.37 41.06 48.37 34.44 49.95 41.96 48.37 48.70 54.42 50.96 50.26
Li_XJTLU_task2_4 LiXJTLU2025 99 52.523 66.93 86.98 58.16 78.04 52.42 57.24 48.42 59.52 50.63 54.88 49.21 76.46 68.00 76.18 54.42 60.56 50.63 42.64 50.44 58.16 35.28 52.42 27.60 48.42 39.96 50.63 52.26 49.21 79.66 68.00 45.44 54.42 40.86 50.63
Wang_ZJU_task2_1 WangZJU2025 107 50.229 65.41 81.54 48.53 71.14 52.16 72.30 51.95 73.90 51.21 64.38 52.11 59.24 60.37 58.96 54.95 51.96 56.16 38.99 21.00 48.53 41.12 52.16 41.54 51.95 32.68 51.21 48.22 52.11 57.12 60.37 39.80 54.95 65.78 56.16
Wang_ZJU_task2_2 WangZJU2025 64 55.589 68.93 73.50 53.32 75.60 50.89 73.76 50.37 80.10 51.58 62.92 53.68 73.96 68.47 63.80 55.00 55.28 53.95 47.59 52.54 53.32 34.86 50.89 38.50 50.37 35.62 51.58 57.60 53.68 75.60 68.47 50.54 55.00 62.70 53.95
Wang_ZJU_task2_3 WangZJU2025 85 53.763 69.17 90.16 53.16 69.56 52.16 73.64 54.05 73.50 53.42 67.56 50.84 64.70 60.74 68.06 54.63 55.40 56.21 43.64 33.26 53.16 40.96 52.16 45.08 54.05 41.28 53.42 45.14 50.84 61.30 60.74 35.48 54.63 63.36 56.21
Wang_ZJU_task2_4 WangZJU2025 55 56.866 71.72 82.42 54.53 74.44 50.05 75.68 51.84 80.42 52.32 66.80 55.00 69.82 67.58 69.54 57.00 60.02 54.84 48.48 50.22 54.53 34.36 50.05 41.52 51.84 42.46 52.32 52.90 55.00 74.94 67.58 51.46 57.00 59.94 54.84
Lin_IASP_task2_1 LinIASP2025 105 51.076 56.54 62.84 49.47 74.78 51.32 51.58 52.89 58.64 50.84 49.84 51.05 53.58 52.89 55.64 51.89 52.44 48.32 46.61 52.08 49.47 29.02 51.32 51.28 52.89 52.72 50.84 45.74 51.05 56.78 52.89 46.96 51.89 53.32 48.32
Lin_IASP_task2_2 LinIASP2025 78 54.420 59.70 93.88 73.00 67.40 51.16 59.14 50.11 54.60 49.42 68.64 53.05 56.84 58.79 54.18 52.84 44.10 51.95 50.15 75.84 73.00 36.98 51.16 37.24 50.11 46.70 49.42 51.16 53.05 63.58 58.79 45.56 52.84 72.36 51.95
Lin_IASP_task2_3 LinIASP2025 74 54.548 63.20 93.86 71.37 74.78 51.32 70.94 48.68 57.92 53.42 68.64 53.05 57.02 61.89 56.10 53.05 47.04 54.32 47.51 74.12 71.37 29.02 51.32 40.96 48.68 42.14 53.42 51.16 53.05 65.52 61.89 41.24 53.05 75.64 54.32
Lin_IASP_task2_4 LinIASP2025 73 54.776 63.29 93.68 69.58 67.40 51.16 63.62 51.42 54.00 49.74 54.20 53.26 59.22 58.74 61.94 54.68 65.88 50.47 48.67 66.64 69.58 36.98 51.16 44.14 51.42 43.50 49.74 52.42 53.26 63.76 58.74 49.04 54.68 46.46 50.47
Lobanov_ITMO_task2_1 LobanovITMO2025 110 49.581 51.50 84.56 49.84 55.00 51.37 46.56 51.95 48.56 50.53 56.14 51.11 48.16 49.58 40.80 49.58 49.56 54.32 46.56 26.84 49.84 50.90 51.37 47.78 51.95 53.48 50.53 56.28 51.11 50.56 49.58 46.58 49.58 61.44 54.32
Lobanov_ITMO_task2_2 LobanovITMO2025 98 52.526 52.41 83.66 62.26 56.88 49.89 43.02 51.74 54.82 52.89 49.76 50.42 48.32 49.74 45.80 51.21 52.68 49.16 53.28 55.14 62.26 59.16 49.89 44.68 51.74 59.78 52.89 56.64 50.42 58.38 49.74 50.26 51.21 46.92 49.16
Qian_nivic_task2_1 Qiannivic2025 32 57.835 57.06 71.54 76.00 60.26 53.47 59.26 51.58 41.12 53.32 56.82 57.21 66.42 58.47 62.08 54.53 50.84 49.11 60.84 93.76 76.00 55.22 53.47 53.48 51.58 53.94 53.32 74.58 57.21 78.78 58.47 56.72 54.53 46.00 49.11
Qian_nivic_task2_2 Qiannivic2025 28 58.020 58.29 78.09 56.10 60.26 53.47 59.26 51.58 41.12 53.32 61.22 61.26 68.76 64.47 62.08 54.53 50.84 49.11 60.98 87.47 56.10 55.22 53.47 53.48 51.58 53.94 53.32 76.80 61.26 83.16 64.47 56.72 54.53 46.00 49.11
Qian_nivic_task2_3 Qiannivic2025 49 57.130 55.47 70.68 74.32 60.26 53.47 59.26 51.58 40.20 51.53 55.82 58.84 59.78 52.00 56.50 53.05 51.60 50.95 61.43 93.36 74.32 55.22 53.47 53.48 51.58 55.16 51.53 73.48 58.84 79.72 52.00 56.48 53.05 48.26 50.95
Qian_nivic_task2_4 Qiannivic2025 39 57.666 56.93 76.71 56.10 60.26 53.47 59.26 51.58 40.20 51.53 60.26 63.37 64.60 62.26 56.50 53.05 51.60 50.95 61.53 87.33 56.10 55.22 53.47 53.48 51.58 55.16 51.53 76.10 63.37 82.92 62.26 56.48 53.05 48.26 50.95
Wang_MYPS_task2_1 WangMYPS2025 16 59.266 56.35 68.40 72.00 58.96 50.79 61.00 53.21 38.14 49.47 62.16 51.79 91.16 85.32 63.58 53.58 40.00 52.68 65.73 96.62 72.00 56.08 50.79 56.94 53.21 61.72 49.47 68.74 51.79 97.54 85.32 58.60 53.58 55.84 52.68
Wang_MYPS_task2_2 WangMYPS2025 20 58.804 57.22 79.57 56.10 58.96 50.79 61.00 53.21 38.14 49.47 65.58 55.16 85.55 71.87 63.58 53.58 40.00 52.68 65.51 88.05 56.10 56.08 50.79 56.94 53.21 61.72 49.47 71.72 55.16 97.54 71.87 58.60 53.58 55.84 52.68
Wang_MYPS_task2_3 WangMYPS2025 1 61.628 61.98 71.42 77.05 63.56 51.63 60.70 52.16 65.36 53.79 64.16 54.05 90.42 79.16 63.94 54.05 39.56 52.84 65.74 92.52 77.05 64.90 51.63 55.42 52.16 59.78 53.79 74.08 54.05 90.06 79.16 61.40 54.05 50.46 52.84
Wang_MYPS_task2_4 WangMYPS2025 4 61.042 62.86 80.21 56.10 63.56 51.63 60.70 52.16 65.36 53.79 68.56 58.47 84.76 67.89 63.94 54.05 39.56 52.84 65.74 88.13 56.10 64.90 51.63 55.42 52.16 59.78 53.79 77.20 58.47 90.08 67.89 61.40 54.05 50.46 52.84
Emon_HDK_task2_1 EmonHDK2025 121 45.151 40.08 19.20 52.26 72.60 48.47 66.32 52.21 38.04 52.68 43.05 49.58 51.87 48.58 38.90 48.32 41.42 51.84 46.16 74.04 52.26 23.38 48.47 75.60 52.21 59.44 52.68 44.78 49.58 55.27 48.58 36.71 48.32 51.72 51.84
Fu_CUMT_task2_1 FuCUMT2025 52 57.023 55.18 70.34 77.16 57.32 56.11 56.56 50.79 41.16 49.32 58.56 58.21 60.84 52.79 56.92 55.37 49.36 50.11 61.06 94.18 77.16 57.12 56.11 53.22 50.79 60.30 49.32 71.90 58.21 82.42 52.79 54.50 55.37 43.24 50.11
Fu_CUMT_task2_2 FuCUMT2025 40 57.585 56.79 76.99 56.10 57.32 56.11 56.56 50.79 41.16 49.32 64.06 62.95 66.56 63.26 56.92 55.37 49.36 50.11 61.27 87.87 56.10 57.12 56.11 53.22 50.79 60.30 49.32 75.74 62.95 85.92 63.26 54.50 55.37 43.24 50.11
Fu_CUMT_task2_3 FuCUMT2025 41 57.564 54.96 70.34 77.16 51.68 54.95 61.18 57.53 41.16 49.32 58.56 58.21 60.84 52.79 56.92 55.37 49.36 50.11 62.30 94.18 77.16 58.92 54.95 59.78 57.53 60.30 49.32 71.90 58.21 82.42 52.79 54.50 55.37 43.24 50.11
Fu_CUMT_task2_4 FuCUMT2025 26 58.137 56.56 76.99 56.10 51.68 54.95 61.18 57.53 41.16 49.32 64.06 62.95 66.56 63.26 56.92 55.37 49.36 50.11 62.51 87.87 56.10 58.92 54.95 59.78 57.53 60.30 49.32 75.74 62.95 85.92 63.26 54.50 55.37 43.24 50.11
Ding_HFUU_task2_1 DingHFUU2025 71 55.130 68.58 91.26 65.89 71.94 51.00 73.66 51.53 67.92 55.16 70.30 54.05 64.24 56.89 72.58 53.47 50.18 54.58 46.17 57.10 65.89 32.50 51.00 40.60 51.53 41.40 55.16 52.68 54.05 69.76 56.89 34.52 53.47 71.92 54.58
Ding_HFUU_task2_2 DingHFUU2025 81 54.303 69.05 89.60 60.74 73.36 50.21 73.50 50.89 69.70 55.05 72.14 54.26 74.64 58.47 70.16 51.37 46.28 52.58 44.97 51.54 60.74 30.40 50.21 46.30 50.89 42.66 55.05 46.96 54.26 69.42 58.47 32.96 51.37 68.92 52.58
Ding_HFUU_task2_3 DingHFUU2025 91 53.158 68.29 87.12 52.42 70.42 51.58 73.26 52.84 76.52 52.68 66.70 50.79 61.98 59.47 67.46 54.89 53.18 55.74 43.17 31.84 52.42 40.92 51.58 43.58 52.84 41.72 52.68 44.26 50.79 61.22 59.47 36.20 54.89 62.56 55.74
Ding_HFUU_task2_4 DingHFUU2025 59 56.378 72.08 85.54 51.95 76.26 49.47 75.56 52.11 81.50 52.21 67.32 53.89 68.90 67.84 69.46 57.32 59.14 54.32 47.69 53.70 51.95 33.52 49.47 41.32 52.11 38.92 52.21 52.06 53.89 71.68 67.84 51.68 57.32 59.18 54.32
Yang_NBU_task2_1 YangNBU2025 3 61.201 65.32 76.16 75.37 60.72 57.79 53.80 49.63 64.42 53.37 75.52 61.32 92.02 80.00 69.42 53.21 49.36 49.74 60.38 95.56 75.37 73.28 57.79 46.86 49.63 61.62 53.37 75.76 61.32 96.52 80.00 48.10 53.21 37.78 49.74
Yang_NBU_task2_2 YangNBU2025 6 60.447 65.67 81.01 56.10 60.72 57.79 53.80 49.63 64.42 53.37 78.62 65.84 86.83 70.03 69.42 53.21 49.36 49.74 60.22 88.35 56.10 73.28 57.79 46.86 49.63 61.62 53.37 78.56 65.84 96.96 70.03 48.10 53.21 37.78 49.74
Yang_NBU_task2_3 YangNBU2025 5 60.950 63.02 73.86 80.21 61.72 55.21 57.10 51.32 67.26 53.58 75.54 60.58 92.32 80.79 64.62 53.63 39.56 50.05 61.27 96.28 80.21 67.20 55.21 53.10 51.32 62.18 53.58 75.38 60.58 92.88 80.79 48.52 53.63 38.83 50.05
Yang_NBU_task2_4 YangNBU2025 8 59.924 63.30 79.67 56.10 61.72 55.21 57.10 51.32 67.26 53.58 77.42 63.89 86.42 68.53 64.62 53.63 39.56 50.05 60.99 88.29 56.10 67.20 55.21 53.10 51.32 62.18 53.58 77.36 63.89 92.94 68.53 48.52 53.63 38.83 50.05
Kret_CU_task2_1 KretCU2025 115 47.903 63.05 70.30 48.42 55.58 50.32 57.20 49.26 72.78 49.63 57.52 51.21 59.68 62.79 73.32 54.74 63.84 49.79 36.47 21.22 48.42 46.02 50.32 37.76 49.26 21.34 49.63 47.40 51.21 62.46 62.79 45.76 54.74 54.98 49.79
Zheng_SJTU-AITHU_task2_1 ZhengSJTU-AITHU2025 13 59.370 60.48 88.30 79.74 64.26 58.53 54.06 47.53 54.70 55.58 64.68 54.74 64.16 51.26 71.14 57.00 42.56 52.11 62.11 94.56 79.74 72.38 58.53 50.50 47.53 60.84 55.58 57.40 54.74 66.08 51.26 57.08 57.00 55.24 52.11
Zheng_SJTU-AITHU_task2_2 ZhengSJTU-AITHU2025 11 59.500 58.73 92.42 85.58 61.80 58.95 56.38 47.58 50.60 55.32 59.34 54.37 67.52 53.21 73.46 56.00 37.82 52.95 63.76 96.88 85.58 75.80 58.95 48.72 47.58 63.48 55.32 57.14 54.37 66.90 53.21 57.06 56.00 63.68 52.95
Zheng_SJTU-AITHU_task2_3 ZhengSJTU-AITHU2025 15 59.314 58.30 93.54 86.79 60.72 57.89 55.56 47.42 50.42 55.05 58.00 54.68 66.50 53.21 73.58 55.89 37.92 52.74 63.79 96.94 86.79 76.88 57.89 47.56 47.42 63.50 55.05 57.68 54.68 66.56 53.21 56.04 55.89 66.18 52.74
Zheng_SJTU-AITHU_task2_4 ZhengSJTU-AITHU2025 12 59.441 58.52 92.44 85.16 61.50 58.47 56.42 47.58 50.50 55.00 58.74 54.37 67.18 53.58 73.28 55.53 37.68 52.95 63.97 96.98 85.16 75.92 58.47 48.82 47.58 64.30 55.00 56.92 54.37 66.94 53.58 56.82 55.53 64.78 52.95
Zhao_CUMT_task2_1 ZhaoCUMT2025 102 51.655 53.52 66.12 61.42 58.96 51.95 41.08 49.26 55.48 49.11 52.95 48.47 43.94 52.00 65.52 54.95 55.16 51.00 49.61 64.48 61.42 48.32 51.95 44.84 49.26 48.40 49.11 35.27 48.47 62.30 52.00 57.78 54.95 49.04 51.00
Zhao_CUMT_task2_2 ZhaoCUMT2025 101 52.094 53.98 68.56 61.26 53.40 50.84 61.78 49.53 56.00 49.74 50.64 50.11 40.64 51.11 61.62 55.68 49.32 49.79 50.43 56.50 61.26 48.18 50.84 51.56 49.53 36.04 49.74 45.36 50.11 75.02 51.11 55.21 55.68 51.14 49.79
Zhao_CUMT_task2_3 ZhaoCUMT2025 61 56.057 68.15 58.68 51.05 75.22 50.89 76.74 50.26 73.80 53.37 70.10 56.84 77.80 68.63 59.48 54.26 60.46 54.21 48.83 61.06 51.05 35.52 50.89 39.02 50.26 39.80 53.37 56.60 56.84 82.46 68.63 45.86 54.26 58.98 54.21
Zhao_CUMT_task2_4 ZhaoCUMT2025 62 55.784 64.73 64.12 51.95 74.68 51.63 66.86 51.37 82.94 52.42 55.22 51.63 65.48 66.37 64.18 55.74 53.66 54.00 50.45 63.32 51.95 39.02 51.63 39.26 51.37 38.42 52.42 59.22 51.63 74.40 66.37 50.46 55.74 64.48 54.00
Ozeki_MELCO_task2_1 OzekiMELCO2025 23 58.234 66.73 85.18 74.79 67.36 55.79 71.48 51.05 57.84 50.63 73.04 55.63 53.22 49.42 73.48 56.89 62.74 55.11 54.17 87.56 74.79 57.50 55.79 34.30 51.05 55.22 50.63 54.46 55.63 51.42 49.42 56.90 56.89 61.68 55.11
Ozeki_MELCO_task2_2 OzekiMELCO2025 60 56.122 63.37 83.72 71.00 64.14 53.58 71.02 48.95 52.70 50.42 72.60 55.53 50.92 49.74 74.60 54.79 53.10 51.89 52.37 88.92 71.00 52.70 53.58 31.24 48.95 56.78 50.42 51.58 55.53 53.00 49.74 56.14 54.79 59.38 51.89
Ozeki_MELCO_task2_3 OzekiMELCO2025 69 55.296 63.57 83.32 70.26 64.14 53.58 69.52 49.74 55.10 48.37 72.60 55.53 50.92 49.74 74.20 55.00 53.10 51.89 50.33 88.72 70.26 52.70 53.58 28.12 49.74 49.26 48.37 51.58 55.53 53.00 49.74 56.40 55.00 59.38 51.89
Ozeki_MELCO_task2_4 OzekiMELCO2025 79 54.407 62.80 85.30 58.00 62.92 53.63 70.44 52.58 60.14 50.63 73.02 53.68 46.36 49.11 71.52 50.00 50.74 51.84 49.76 64.36 58.00 59.20 53.63 35.80 52.58 51.00 50.63 51.08 53.68 46.86 49.11 51.76 50.00 48.60 51.84
Huang_XJU_task2_1 HuangXJU2025 25 58.141 68.60 76.72 53.63 64.98 59.37 74.72 49.21 69.64 52.79 61.63 50.42 76.74 69.32 77.02 57.68 54.92 51.00 53.26 71.48 53.63 51.00 59.37 34.26 49.21 62.14 52.79 45.10 50.42 88.36 69.32 51.58 57.68 54.16 51.00
Huang_XJU_task2_2 HuangXJU2025 27 58.070 66.34 58.74 49.37 68.52 56.05 87.26 51.63 64.84 51.89 65.16 50.32 73.30 63.11 66.74 59.05 55.20 52.16 55.50 57.08 49.37 47.90 56.05 56.38 51.63 59.86 51.89 42.84 50.32 84.36 63.11 53.46 59.05 57.46 52.16
Huang_XJU_task2_3 HuangXJU2025 35 57.739 67.57 72.54 52.26 68.58 56.16 75.16 49.42 62.86 51.95 67.82 49.95 74.94 65.68 73.45 58.32 52.32 54.11 53.35 67.28 52.26 50.68 56.16 36.34 49.42 63.64 51.95 43.40 49.95 88.24 65.68 48.42 58.32 58.44 54.11
Huang_XJU_task2_4 HuangXJU2025 37 57.706 63.50 55.60 48.53 59.00 58.68 86.30 52.21 58.10 52.26 68.64 50.95 76.48 68.11 64.22 57.00 52.54 52.16 55.96 45.38 48.53 57.18 58.68 56.24 52.21 65.14 52.26 44.56 50.95 84.94 68.11 56.48 57.00 54.42 52.16
Fujimura_NU_task2_1 FujimuraNU2025 7 59.995 75.36 99.30 65.53 74.40 61.84 72.14 52.00 67.84 53.68 76.50 58.47 74.92 68.89 79.70 57.05 66.34 51.89 51.22 64.36 65.53 74.14 61.84 38.68 52.00 61.76 53.68 51.82 58.47 95.16 68.89 44.76 57.05 30.34 51.89
Fujimura_NU_task2_2 FujimuraNU2025 21 58.510 71.82 95.26 61.11 63.08 58.95 75.88 50.89 75.96 55.21 62.88 51.37 80.68 66.11 65.58 58.00 65.98 51.00 51.20 74.62 61.11 74.84 58.95 36.14 50.89 53.68 55.21 44.40 51.37 84.02 66.11 50.86 58.00 34.36 51.00
Fujimura_NU_task2_3 FujimuraNU2025 14 59.343 77.44 97.86 64.68 75.36 61.89 75.86 49.58 73.60 54.95 77.20 54.95 82.80 73.05 76.84 58.16 66.64 51.53 49.19 58.18 64.68 71.74 61.89 36.22 49.58 55.72 54.95 45.60 54.95 97.36 73.05 46.42 58.16 31.04 51.53
Fujimura_NU_task2_4 FujimuraNU2025 9 59.908 75.83 99.22 65.00 70.66 60.84 74.34 50.89 70.90 55.26 77.78 55.00 78.04 67.95 79.20 58.89 64.86 52.16 51.12 61.02 65.00 73.30 60.84 36.54 50.89 59.44 55.26 49.50 55.00 98.02 67.95 44.98 58.89 33.74 52.16
Jiang_THUEE_task2_1 JiangTHUEE2025 19 58.892 58.01 93.42 86.37 58.90 56.95 55.24 47.53 50.40 54.68 56.34 53.95 66.70 53.79 72.28 55.79 38.90 52.47 62.97 96.96 86.37 77.58 56.95 47.58 47.53 63.72 54.68 55.38 53.95 65.70 53.79 54.80 55.79 64.10 52.47
Jiang_THUEE_task2_2 JiangTHUEE2025 10 59.793 59.48 92.46 86.21 60.50 58.26 57.46 47.37 50.80 55.89 61.60 54.68 68.98 56.89 73.98 56.37 38.72 51.47 63.45 97.64 86.21 77.48 58.26 48.60 47.37 59.42 55.89 57.80 54.68 71.30 56.89 57.42 56.37 59.58 51.47
Jiang_THUEE_task2_3 JiangTHUEE2025 18 59.074 58.13 93.56 87.11 58.22 56.00 56.56 47.42 50.00 56.16 59.14 54.37 68.18 54.53 73.52 56.00 37.16 51.84 63.23 96.98 87.11 78.84 56.00 48.08 47.42 60.26 56.16 55.30 54.37 68.64 54.53 56.78 56.00 63.00 51.84
Jiang_THUEE_task2_4 JiangTHUEE2025 17 59.156 58.13 93.94 87.58 57.02 56.32 56.26 47.37 49.82 55.63 59.18 54.21 68.40 55.68 73.82 55.74 37.68 52.21 63.33 97.68 87.58 79.42 56.32 47.88 47.37 59.48 55.63 56.46 54.21 70.16 55.68 55.80 55.74 62.88 52.21
Bian_TGU_task2_1 BianTGU2025 119 46.576 40.69 42.08 50.21 37.36 49.47 41.96 48.63 28.78 48.37 44.62 51.05 46.16 48.68 45.76 52.42 46.32 50.95 50.48 54.04 50.21 64.12 49.47 46.72 48.63 62.08 48.37 45.42 51.05 48.96 48.68 51.96 52.42 39.74 50.95
Bian_TGU_task2_2 BianTGU2025 116 47.851 48.64 41.56 49.00 68.62 50.32 51.56 51.42 47.92 49.16 46.56 50.95 45.12 52.53 51.96 49.74 44.08 49.05 44.98 41.82 49.00 28.22 50.32 46.70 51.42 51.86 49.16 52.90 50.95 51.24 52.53 54.86 49.74 47.24 49.05
Bian_TGU_task2_3 BianTGU2025 104 51.417 52.23 44.06 49.79 57.54 50.89 53.98 51.05 58.20 51.63 49.02 48.16 52.72 51.84 53.10 51.68 52.16 51.53 51.24 44.44 49.79 52.92 50.89 45.30 51.05 56.52 51.63 43.98 48.16 62.92 51.84 51.82 51.68 58.76 51.53
Bian_TGU_task2_4 BianTGU2025 120 46.193 50.08 45.74 49.79 76.74 49.58 46.58 47.58 62.70 49.74 44.14 48.95 44.78 50.11 45.98 52.16 48.28 49.26 40.29 52.94 49.79 24.74 49.58 33.92 47.58 40.04 49.74 45.62 48.95 46.98 50.11 47.50 52.16 48.70 49.26
Sera_TMU_task2_1 SeraTMU2025 57 56.568 72.13 62.84 52.00 77.24 54.05 84.42 53.21 65.50 50.58 76.16 49.47 77.90 67.21 77.70 55.74 62.10 51.32 48.62 53.30 52.00 40.02 54.05 47.66 53.21 42.98 50.58 36.24 49.47 89.72 67.21 48.42 55.74 58.30 51.32
Kim_DAU_task2_1 KimDAU2025 113 48.537 44.94 63.84 52.00 34.26 49.79 60.14 51.95 31.98 49.74 47.44 50.74 39.70 49.95 51.30 48.84 51.24 49.58 50.83 78.06 52.00 63.10 49.79 55.02 51.95 44.96 49.74 41.22 50.74 54.16 49.95 34.90 48.84 59.02 49.58
Kim_DAU_task2_2 KimDAU2025 111 48.966 50.52 63.80 49.16 37.92 50.84 45.90 49.89 60.62 56.05 49.96 50.11 46.02 51.95 52.14 48.11 58.44 50.37 45.97 55.08 49.16 53.08 50.84 35.54 49.89 55.16 56.05 45.44 50.11 54.66 51.95 39.70 48.11 39.56 50.37
Wang_UniS_task2_1 WangUniS2025 34 57.754 62.96 85.42 72.84 69.62 55.00 73.40 51.26 52.36 54.11 75.38 53.05 47.24 52.84 79.32 57.63 47.10 53.84 55.21 87.80 72.84 50.72 55.00 38.62 51.26 72.66 54.11 42.46 53.05 75.44 52.84 53.46 57.63 53.72 53.84
Wang_UniS_task2_2 WangUniS2025 46 57.261 64.46 84.00 69.79 71.52 56.63 73.72 51.53 52.72 55.58 76.90 53.05 49.66 51.63 80.42 57.37 49.74 52.63 52.98 85.38 69.79 49.80 56.63 36.56 51.53 72.24 55.58 42.40 53.05 72.90 51.63 53.10 57.37 45.72 52.63
Wang_UniS_task2_3 WangUniS2025 53 56.975 59.99 90.14 63.47 55.16 55.58 60.92 50.05 51.12 53.89 61.86 48.84 63.14 62.42 78.86 57.63 42.62 50.16 56.41 71.32 63.47 67.34 55.58 42.16 50.05 60.96 53.89 44.10 48.84 68.94 62.42 49.18 57.63 65.28 50.16
Wang_UniS_task2_4 WangUniS2025 90 53.190 59.95 80.74 70.11 66.28 51.63 62.00 52.53 62.94 51.68 61.64 52.68 39.64 47.37 72.38 52.68 53.50 53.16 47.66 55.94 70.11 42.64 51.63 40.16 52.53 31.18 51.68 48.88 52.68 93.32 47.37 44.16 52.68 63.54 53.16
Guan_HEU_task2_1 GuanHEU2025 22 58.253 72.85 84.14 59.53 68.38 53.63 75.56 49.58 69.48 50.74 77.48 56.11 81.90 77.26 80.50 61.79 55.12 51.89 49.80 61.12 59.53 46.72 53.63 33.64 49.58 38.30 50.74 51.44 56.11 99.82 77.26 50.66 61.79 56.08 51.89
Guan_HEU_task2_2 GuanHEU2025 48 57.211 72.14 76.94 53.37 68.16 52.95 75.44 50.11 70.02 50.42 77.72 56.00 80.90 75.42 79.62 61.32 55.86 52.11 48.61 55.34 53.37 45.58 52.95 32.70 50.11 37.24 50.42 50.80 56.00 99.02 75.42 51.28 61.32 56.04 52.11
Guan_HEU_task2_3 GuanHEU2025 117 47.504 64.26 95.46 49.42 74.84 52.11 65.78 49.47 56.56 55.63 54.20 49.84 62.94 56.74 79.76 50.05 47.84 50.00 35.49 20.84 49.42 29.20 52.11 27.34 49.47 65.42 55.63 44.34 49.84 71.56 56.74 32.16 50.05 42.16 50.00
Guan_HEU_task2_4 GuanHEU2025 68 55.318 73.02 86.20 50.00 73.54 54.53 74.90 49.74 69.48 52.26 76.72 55.63 80.22 72.84 81.40 59.11 53.10 51.26 44.80 42.62 50.00 39.32 54.53 28.34 49.74 43.28 52.26 48.94 55.63 99.14 72.84 46.12 59.11 52.36 51.26
Kim_AISTAT_task2_1 KimAISTAT2025 31 57.845 60.99 87.08 77.47 41.18 54.74 78.96 55.47 78.58 61.32 65.24 51.11 54.90 52.00 82.02 55.68 41.20 50.47 56.48 93.06 77.47 82.48 54.74 37.54 55.47 63.20 61.32 41.52 51.11 64.20 52.00 53.02 55.68 56.18 50.47
Kim_AISTAT_task2_2 KimAISTAT2025 33 57.808 60.92 87.80 78.37 40.74 54.58 78.80 55.32 78.14 61.53 64.88 50.84 55.28 51.47 81.96 54.95 41.34 51.00 56.52 93.44 78.37 82.22 54.58 37.48 55.32 63.36 61.53 41.54 50.84 64.22 51.47 53.32 54.95 56.16 51.00
Kim_AISTAT_task2_3 KimAISTAT2025 36 57.733 60.94 89.16 78.05 40.84 54.05 78.82 55.00 76.72 61.32 64.44 51.21 55.38 50.84 81.40 54.47 41.66 51.16 56.53 93.22 78.05 81.84 54.05 37.34 55.00 63.36 61.32 41.86 51.21 65.28 50.84 52.44 54.47 56.40 51.16
Kim_AISTAT_task2_4 KimAISTAT2025 29 57.955 61.27 87.90 77.47 41.46 54.53 79.32 55.32 78.10 61.53 65.44 51.63 55.54 51.58 81.64 55.79 41.46 50.47 56.54 92.64 77.47 82.18 54.53 37.54 55.32 63.16 61.53 42.30 51.63 65.16 51.58 52.18 55.79 55.88 50.47



System characteristics

Summary of the submitted system characteristics.

Rank Submission
Code
Technical
Report
Classifier System
Complexity
Acoustic
Feature
Data
Augmentation
Decision Making System
Embeddings
Subsystem
Conut
External
Data Usage
Front End
System
58 DCASE2025_baseline_task2_MAHALA DCASE2025baseline2025 AE log-mel energies
77 DCASE2025_baseline_task2_MSE DCASE2025baseline2025 AE log-mel energies
100 Zhou_XJU_task2_1 ZhouXJU2025 KNN, Arcface log-mel spectrogram specaug BEATs BEATs
94 Zhou_XJU_task2_2 ZhouXJU2025 KNN, Arcface log-mel spectrogram specaug BEATs BEATs
96 Zhou_XJU_task2_3 ZhouXJU2025 KNN, Arcface log-mel spectrogram specaug BEATs BEATs
93 Zhou_XJU_task2_4 ZhouXJU2025 KNN, Arcface log-mel spectrogram specaug BEATs BEATs
45 Cai_NCUT_task2_1 CaiNCUT2025 EAT log-mel energies
83 Cai_NCUT_task2_2 CaiNCUT2025 AE log-mel energies EAT
42 Cai_NCUT_task2_3 CaiNCUT2025 ensemble log-mel energies EAT, M2D
84 Saengthong_SCITOK_task2_1 SaengthongSCITOK2025 ensemble log-mel energies average 5
2 Saengthong_SCITOK_task2_2 SaengthongSCITOK2025 ensemble log-mel energies average 5
56 Saengthong_SCITOK_task2_3 SaengthongSCITOK2025 ensemble log-mel energies average BEATs, M2D-CLAP, EAT, SSLAM, CED 5
80 Saengthong_SCITOK_task2_4 SaengthongSCITOK2025 ensemble log-mel energies
88 Zhang_DKU_task2_1 ZhangDKU2025 transformer, AE raw waveform noise augmentation simulation of attribute labels, pre-trained model
70 Zhang_DKU_task2_2 ZhangDKU2025 transformer, AE, ensemble log-mel energies, raw waveform noise augmentation, spectral augmentation average BEATs 3 simulation of attribute labels, pre-trained model
92 Zhang_DKU_task2_3 ZhangDKU2025 transformer, AE, ensemble log-mel energies, raw waveform noise augmentation, spectral augmentation average BEATs 2 simulation of attribute labels, pre-trained model
63 Zhang_DKU_task2_4 ZhangDKU2025 transformer, AE, ensemble log-mel energies, raw waveform noise augmentation, spectral augmentation average BEATs 2 simulation of attribute labels, pre-trained model
66 WT_IACAS_task2_1 WTIACAS2025 ResNet, ensemble log-mel energies BEATs, EAT, SSLAM
44 WT_IACAS_task2_2 WTIACAS2025 ResNet, ensemble log-mel energies BEATs, EAT, SSLAM
86 WT_IACAS_task2_3 WTIACAS2025 ResNet, ensemble log-mel energies BEATs, EAT, SSLAM
76 WT_IACAS_task2_4 WTIACAS2025 ResNet, ensemble log-mel energies BEATs, EAT, SSLAM
24 Zhou_XAUAT_task2_1 ZhouXAUAT2025 AE, KNN log-mel energies mixup, specaug, smote
43 Zhou_XAUAT_task2_2 ZhouXAUAT2025 AE, KNN log-mel energies mixup, specaug, smote
95 Zhou_XAUAT_task2_3 ZhouXAUAT2025 AE, LOF log-mel energies mixup, specaug, smote
50 Zhou_XAUAT_task2_4 ZhouXAUAT2025 AE, KNN log-mel energies mixup, specaug
54 Zhong_USTC_task2_1 ZhongUSTC2025 KNN log-mel energies mixup, addnoise average 2 embeddings, pre-trained model sound separation
51 Zhong_USTC_task2_2 ZhongUSTC2025 KNN log-mel energies mixup, addnoise average 2 embeddings, pre-trained model sound separation
38 Zhong_USTC_task2_3 ZhongUSTC2025 KNN log-mel energies mixup, addnoise average 2 embeddings, pre-trained model sound separation
30 Zhong_USTC_task2_4 ZhongUSTC2025 KNN log-mel energies mixup, addnoise average 2 embeddings, pre-trained model sound separation
109 Vijayyan_SNUC_task2_1 VijayyanSNUC2025 contrastive learning log-mel energies RandomResizedCrop, RandomHorizontalFlip, ColorJitter, RandomGrayscale
97 CHUNG_KUCAU_task2_1 CHUNGKUCAU2025 pre-trained model, KNN log mel spectrogram BEATs zero padding or truncated to 10 seconds
65 CHUNG_KUCAU_task2_2 CHUNGKUCAU2025 pre-trained model, KNN log mel spectrogram BEATs zero padding or truncated to 10 seconds
72 CHUNG_KUCAU_task2_3 CHUNGKUCAU2025 pre-trained model, KNN log mel spectrogram BEATs zero padding or truncated to 10 seconds
47 CHUNG_KUCAU_task2_4 CHUNGKUCAU2025 pre-trained model, KNN log mel spectrogram BEATs zero padding or truncated to 10 seconds
112 Dung_CNTT1PTIT_task2_1 DungCNTT1PTIT2025 CNN, Ensemble FFT, Magnitude Spectrogram Mixup, SpecAugment, Random Crop/Padding average 2
103 Zhang_NWPU_task2_1 ZhangNWPU2025 transformer, knn, normalizing flow, ensemble fbank SMOTE weighted average BEATs, EAT 6 pre-trained model
67 Zhang_NWPU_task2_2 ZhangNWPU2025 transformer, knn, normalizing flow, ensemble fbank SMOTE weighted average BEATs, EAT 6 pre-trained model
75 Zhang_NWPU_task2_3 ZhangNWPU2025 transformer, knn, normalizing flow, ensemble fbank SMOTE weighted average BEATs, EAT 6 pre-trained model
82 Zhang_NWPU_task2_4 ZhangNWPU2025 transformer, knn, normalizing flow, ensemble fbank SMOTE weighted average BEATs, EAT 6 pre-trained model
118 Chao_BUCT_task2_1 ChaoBUCT2025 CNN STFT,FFT mixup average zero-padding
114 Chao_BUCT_task2_2 ChaoBUCT2025 CNN STFT,FFT mixup average zero-padding
108 Chao_BUCT_task2_3 ChaoBUCT2025 Attention, CNN, AE STFT mixup
89 Li_XJTLU_task2_1 LiXJTLU2025 KNN raw waveform mixup average BEATs
87 Li_XJTLU_task2_2 LiXJTLU2025 KNN raw waveform mixup average BEATs
106 Li_XJTLU_task2_3 LiXJTLU2025 KNN raw waveform mixup average BEATs
99 Li_XJTLU_task2_4 LiXJTLU2025 KNN raw waveform mixup average BEATs
107 Wang_ZJU_task2_1 WangZJU2025 AE, CNN, BiGRU, BEATs log-mel energies
64 Wang_ZJU_task2_2 WangZJU2025 AE, CNN, BiGRU, BEATs log-mel energies
85 Wang_ZJU_task2_3 WangZJU2025 AE, CNN, BiGRU, BEATs log-mel energies
55 Wang_ZJU_task2_4 WangZJU2025 AE, CNN, BiGRU, BEATs log-mel energies
105 Lin_IASP_task2_1 LinIASP2025 AE log-mel energies
78 Lin_IASP_task2_2 LinIASP2025 AE log-mel energies
74 Lin_IASP_task2_3 LinIASP2025 AE log-mel energies
73 Lin_IASP_task2_4 LinIASP2025 AE log-mel energies HTS-AT pre-trained model
110 Lobanov_ITMO_task2_1 LobanovITMO2025 AE spectrogram SVD
98 Lobanov_ITMO_task2_2 LobanovITMO2025 AE spectrogram SVD
32 Qian_nivic_task2_1 Qiannivic2025 KNN log-mel energies, spectrogram mixup
28 Qian_nivic_task2_2 Qiannivic2025 KNN log-mel energies, spectrogram mixup
49 Qian_nivic_task2_3 Qiannivic2025 KNN log-mel energies, spectrogram mixup
39 Qian_nivic_task2_4 Qiannivic2025 KNN log-mel energies, spectrogram mixup
16 Wang_MYPS_task2_1 WangMYPS2025 EAT log-mel energies
20 Wang_MYPS_task2_2 WangMYPS2025 EAT log-mel energies
1 Wang_MYPS_task2_3 WangMYPS2025 EAT log-mel energies
4 Wang_MYPS_task2_4 WangMYPS2025 EAT log-mel energies
121 Emon_HDK_task2_1 EmonHDK2025 AE, GRL, Deep SVDD log-mel energies Synthetic Anomaly Augmentation, noise bursts, frequency shifts
52 Fu_CUMT_task2_1 FuCUMT2025 KNN log-mel energies minmum sound separation
40 Fu_CUMT_task2_2 FuCUMT2025 KNN log-mel energies minmum sound separation
41 Fu_CUMT_task2_3 FuCUMT2025 KNN log-mel energies minmum sound separation
26 Fu_CUMT_task2_4 FuCUMT2025 KNN log-mel energies minmum sound separation
71 Ding_HFUU_task2_1 DingHFUU2025 VQ-VAE, PixelSNAIL log-mel energies average 2
81 Ding_HFUU_task2_2 DingHFUU2025 VQ-VAE, PixelSNAIL log-mel energies average 2 HPSS
91 Ding_HFUU_task2_3 DingHFUU2025 AE log-mel energies
59 Ding_HFUU_task2_4 DingHFUU2025 normalizing flow log-mel energies mixup
3 Yang_NBU_task2_1 YangNBU2025 AE log-mel energies
6 Yang_NBU_task2_2 YangNBU2025 AE log-mel energies
5 Yang_NBU_task2_3 YangNBU2025 AE log-mel energies
8 Yang_NBU_task2_4 YangNBU2025 AE log-mel energies
115 Kret_CU_task2_1 KretCU2025 k-NN raw waveform none HuBERT pre-trained model
13 Zheng_SJTU-AITHU_task2_1 ZhengSJTU-AITHU2025 pre-trained models, ensemble fbank specaug, add noise median 36 Audioset, Freesound, MTG-Jamendo, Music4all, BEATs, EAT
11 Zheng_SJTU-AITHU_task2_2 ZhengSJTU-AITHU2025 pre-trained models, ensemble STFT, fbank specaug, add noise median 51 Audioset, Freesound, MTG-Jamendo, Music4all, BEATs, EAT
15 Zheng_SJTU-AITHU_task2_3 ZhengSJTU-AITHU2025 pre-trained models, ensemble STFT, fbank specaug, add noise median 21 Audioset, Freesound, MTG-Jamendo, Music4all, BEATs, EAT
12 Zheng_SJTU-AITHU_task2_4 ZhengSJTU-AITHU2025 pre-trained models, ensemble STFT, fbank specaug, add noise median 21 Audioset, Freesound, MTG-Jamendo, Music4all, BEATs, EAT
102 Zhao_CUMT_task2_1 ZhaoCUMT2025 MobileFaceNet log-mel energies specaug BEATs
101 Zhao_CUMT_task2_2 ZhaoCUMT2025 MobileFaceNet log-mel energies specaug BEATs
61 Zhao_CUMT_task2_3 ZhaoCUMT2025 AENet log-mel energies BEATs
62 Zhao_CUMT_task2_4 ZhaoCUMT2025 AENet log-mel energies BEATs
23 Ozeki_MELCO_task2_1 OzekiMELCO2025 Contrastive learning based on the SimSiam framework, kNN Mel spectrogram Gain adjustment, Polarity Inversion, Pitch Shifting, Time Stretching, Additive Background Noise CED pre-trained model, embeddings, data augmentation Normalization, Patchification
60 Ozeki_MELCO_task2_2 OzekiMELCO2025 Contrastive learning based on the SimSiam framework, kNN Mel spectrogram Gain adjustment, Polarity Inversion, Pitch Shifting, Time Stretching, Additive Background Noise CED pre-trained model, embeddings, data augmentation Normalization, Patchification
69 Ozeki_MELCO_task2_3 OzekiMELCO2025 Contrastive learning based on the SimSiam framework, kNN Mel spectrogram Gain adjustment, Polarity Inversion, Pitch Shifting, Time Stretching, Additive Background Noise CED pre-trained model, embeddings, data augmentation Normalization, Patchification
79 Ozeki_MELCO_task2_4 OzekiMELCO2025 Contrastive learning based on the SimSiam framework, kNN Mel spectrogram Gain adjustment, Polarity Inversion, Pitch Shifting, Time Stretching, Additive Background Noise CED pre-trained model, embeddings, data augmentation Normalization, Patchification
25 Huang_XJU_task2_1 HuangXJU2025 CNN log-mel energies, spectrum mixup, specaug maximum BEATs pre-trained model
27 Huang_XJU_task2_2 HuangXJU2025 CNN log-mel energies, spectrum mixup, specaug maximum EAT pre-trained model
35 Huang_XJU_task2_3 HuangXJU2025 CNN log-mel energies, spectrum mixup, specaug maximum BEATs, EAT pre-trained model
37 Huang_XJU_task2_4 HuangXJU2025 CNN log-mel energies, spectrum mixup, specaug maximum BEATs, EAT pre-trained model
7 Fujimura_NU_task2_1 FujimuraNU2025 CNN spectrogram, spectrum mixup maximum BEATs, EAT, SSLAM 32 pre-trained model, training of enhancement model DNN-based Enhancement
21 Fujimura_NU_task2_2 FujimuraNU2025 CNN spectrogram, spectrum mixup maximum BEATs, EAT, SSLAM 19 pre-trained model, training of enhancement model DNN-based Enhancement
14 Fujimura_NU_task2_3 FujimuraNU2025 CNN spectrogram, spectrum mixup maximum BEATs, EAT, SSLAM 51 pre-trained model, training of enhancement model DNN-based Enhancement
9 Fujimura_NU_task2_4 FujimuraNU2025 CNN spectrogram, spectrum mixup maximum BEATs, EAT, SSLAM 67 pre-trained model, training of enhancement model DNN-based Enhancement
19 Jiang_THUEE_task2_1 JiangTHUEE2025 pre-trained models, ensemble STFT, fbank specaug median 15 Audioset, Freesound, MTG-Jamendo, Music4all, BEATs, EAT
10 Jiang_THUEE_task2_2 JiangTHUEE2025 pre-trained models, diffusion, ensemble STFT, fbank specaug median 74 Audioset, Freesound, MTG-Jamendo, Music4all, BEATs, EAT, Tangoflux
18 Jiang_THUEE_task2_3 JiangTHUEE2025 pre-trained models, diffusion, ensemble STFT, fbank specaug median 34 Audioset, Freesound, MTG-Jamendo, Music4all, BEATs, EAT
17 Jiang_THUEE_task2_4 JiangTHUEE2025 pre-trained models, diffusion, ensemble STFT, fbank specaug median 38 Audioset, Freesound, MTG-Jamendo, Music4all, BEATs, EAT, Tangoflux
119 Bian_TGU_task2_1 BianTGU2025 MAE log-mel spectrogram mixup
116 Bian_TGU_task2_2 BianTGU2025 MAE log-mel spectrogram mixup
104 Bian_TGU_task2_3 BianTGU2025 MAE log-mel spectrogram mixup
120 Bian_TGU_task2_4 BianTGU2025 MAE log-mel spectrogram mixup
57 Sera_TMU_task2_1 SeraTMU2025 ArcFace, Multi-task learning log-mel energies BEATs
113 Kim_DAU_task2_1 KimDAU2025 VAE, Gradient adcent, CNN STFT
111 Kim_DAU_task2_2 KimDAU2025 LDM, AE Linear Spectrogram Tango, Audio Flamingo 2 Tango, Audio Flamingo 2, LAION-CLAP
34 Wang_UniS_task2_1 WangUniS2025 k-means log-mel energies mixup, specaug BEATs
46 Wang_UniS_task2_2 WangUniS2025 k-means log-mel energies mixup, specaug BEATs
53 Wang_UniS_task2_3 WangUniS2025 k-means log-mel energies mixup, specaug Dasheng
90 Wang_UniS_task2_4 WangUniS2025 k-means log-mel energies mixup
22 Guan_HEU_task2_1 GuanHEU2025 KNN log-mel energies
48 Guan_HEU_task2_2 GuanHEU2025 KNN log-mel energies
117 Guan_HEU_task2_3 GuanHEU2025 KNN log-mel energies
68 Guan_HEU_task2_4 GuanHEU2025 KNN log-mel energies
31 Kim_AISTAT_task2_1 KimAISTAT2025 k-means log-mel spectrogram specaug weighted average BEATs, EAT 6 pre-training
33 Kim_AISTAT_task2_2 KimAISTAT2025 k-means log-mel spectrogram specaug weighted average BEATs, EAT 6 pre-training
36 Kim_AISTAT_task2_3 KimAISTAT2025 k-means log-mel spectrogram specaug weighted average BEATs, EAT 6 pre-training
29 Kim_AISTAT_task2_4 KimAISTAT2025 k-means log-mel spectrogram specaug weighted average BEATs, EAT 6 pre-training



Technical reports

Audio DisMAE: Unsupervised Acoustic Anomaly Detection via Disentangled Masked Autoencoder

Yuren Bian, Jiayun Chen
Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems, Tiangong University, Tianjin, China and Tiangong University, Tianjin, China

Abstract

This technical report presents our submission to DCASE 2025 Task 2, which addresses unsupervised anomalous sound detection under domain shift conditions. We extend the Disentangled Masked Autoencoder (DisMAE), originally proposed for visual domain generalization, to the audio domain. In our approach, machine sounds are first transformed into log-Mel spectrograms and then fed into the DisMAE framework. The semantic branch is designed to reconstruct domain-invariant features, while the variational branch captures domain-specific attributes such as background noise and device variability. By disentangling these two representations, the model achieves robust reconstruction of normal operating sounds. Reconstruction errors from the primary decoder branch are used as anomaly scores. Experimental results demonstrate that the proposed method achieves promising performance on several machine types in the DCASE 2025 dataset.

System characteristics
Classifier MAE
System complexity 11739140, 158256388
Acoustic features log-mel spectrogram
Data augmentation mixup
PDF

NCUT SYSTEM FOR FIRST-SHOT UNSUPERVISED ANOMALOUS SOUND DETECTION

Xichang Cai, Jiafeng Li, Shenghao Liu
School of Artificial Intelligence and Computer Science, North China University of Technology, Beijing, China and North China University of Technology, Beijing, China

Abstract

Anomalous sound detection (ASD) plays a crucial role in machine condition monitoring, especially in scenarios where collecting anomalous data is impractical. In this report, we propose a First-Shot Unsupervised Anomalous Sound Detection method that requires only normal sound recordings during training. Our approach leverages multiple pre-trained audio embedding models to extract rich and diverse feature representations from machine sounds. Each embedding is evaluated using a K-Nearest Neighbors (KNN) algorithm to compute anomaly scores without supervision. To further improve detection performance and robustness, we perform model-level score fusion by combining the outputs from different embedding models. Experiments conducted on public datasets demonstrate that our method achieves competitive performance in first-shot and low-resource settings, with strong generalization capabilities across machine types and environments. This framework offers a practical and scalable solution for industrial anomaly detection applications.

System characteristics
Classifier AE, EAT, ensemble
System complexity 269992, 309409295, 394902289
Acoustic features log-mel energies
System embeddings EAT, EAT, M2D
PDF

The Anomaly Sound Detection Method Based on the Dual-Path CNN and the Autoencoder

Chao Chen, Peng Wu, Pengqi Wang, and Bo Ma
School of Mechanical and Electrical Engineering, Beijing University of Chemical Technology, Beijing, China

Abstract

This report contains a description of the systems submitted to task 2 “First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring” of the DCASE2025 Challenge. The anomaly detection model based on the attention mechanism and the convolutional networks enhanced autoencoder (ACAE) is proposed. In addition, we introduced the DensitySoftmax and the dynamic topic mixture model (DtMM) into the previous unsupervised model to represent the distance between abnormal samples and normal samples. In experimental evaluations, it is shown that both modifications improve the resulting performance and that the proposed. By introducing domain generalization methods, our model achieved improved metrics on the target domain compared to the baseline model.

System characteristics
Classifier AE, Attention, CNN
System complexity 0.55M, 6087766
Acoustic features FFT, STFT
Data augmentation mixup
Decision making average
Front end system zero-padding
PDF

FIRST-SHOT UNSUPERVISED ANOMALOUS SOUND DETECTION SYSTEM BASED ON PRE-TRAINED MODEL

Sanghyeok Chung, Sunmook Choi, Seungeun Lee, Kihwan Lee, Il-Youp Kwak, Seungsang Oh
Department of Mathematics, Korea University, Seoul, South Korea and Center for Applied Mathematics, Cornell University, Ithaca, NY, USA and Department of Statistics and Data Science, Chung-Ang University, Seoul, South Korea

Abstract

This technical report presents our approach for Task 2 of the DCASE2025 Challenge, First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring. To tackle the challenge of detecting anomalous sounds, we utilize a pre-trained model as a feature extractor. We further adapt the model to the task using Low-Rank Adaptation (LoRA), allowing efficient fine-tuning. Anomaly scores are then computed using a k-nearest neighbors algorithm on standardized feature vectors. Experimental results on the development set demonstrate that our proposed system significantly outperforms the official baseline, validating the effectiveness of our approach.

System characteristics
Classifier KNN, pre-trained model
System complexity 90M
Acoustic features log mel spectrogram
System embeddings BEATs
Front end system zero padding or truncated to 10 seconds
PDF

Description and Discussion on DCASE 2024 Challenge Task 2: First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring

Tomoya Nishida, Noboru Harada, Daisuke Niizumi, Davide Albertini, Roberto Sannino, Simone Pradolini, Filippo Augusti, Keisuke Imoto, Kota Dohi, Harsh Purohit, Takashi Endo, Yohei Kawaguchi
Research and Development Group, Hitachi, Ltd., Tokyo, Japan and NTT Communication Science Labs, Kanagawa, Japan and STMicroelectronics, Italy and Doshisha University, Kyoto, Japan

Abstract

We present the task description of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2024 Challenge Task 2: "First-shot unsupervised anomalous sound detection (ASD) for machine condition monitoring". Continuing from last year's DCASE 2023 Challenge Task 2, we organize the task as a first-shot problem under domain generalization required settings. The main goal of the first-shot problem is to enable rapid deployment of ASD systems for new kinds of machines without the need for machine-specific hyperparameter tunings. This problem setting was realized by (i) giving only one section for each machine type and (ii) having completely different machine types for the development and evaluation datasets. For the DCASE 2024 Challenge Task 2, data of completely new machine types were newly collected and provided as the evaluation dataset. In addition, attribute information such as the machine operation conditions were concealed for several machine types to mimic situations where such information are unavailable. We will add challenge results and analysis of the submissions after the challenge submission deadline.

System characteristics
Classifier AE
System complexity 267928
Acoustic features log-mel energies
PDF

Abnormal Sound Detection Based on Domain Generalization

Junkai Ding, Bo Pang, Xingcheng Zhu, Shengbing Chen, Zhifang Zheng
Research and Development Group, Hefei University, Hefei, China

Abstract

This technical report describes the anomalous sound detection system we submitted for DCASE 2025 Task 2. DCASE Task2 aims to solve the core pain points of machine health monitoring in industrial scenarios. Compared to last year’s task, this year’s additional datasets have been added, and small and difficult to detect domain shifts have been added, but the main focus is still on the unsupervised learning framework to achieve the first detection of unknown abnormal sounds from industrial machines, while overcoming the interference of domain shifts. At present, the pain points of this task are: 1.domain shift sensitivity, 2. finite sample learning bottleneck, and 3. complexity of abnormal patterns. In order to solve these problems, we submit four methods for detecting abnormal sounds in machine status,In the first and second methods, we used the joint model composed of VQ-VAE and PixelSNAIL for anomaly detection, and in the third and fourth methods, we used AE and flow models for anomaly detection. All four methods use feature vectors extracted from convolutional neural networks to identify anomalous sounds through anomaly detection algorithms. Experiments on the development set show that the performance of these four methods is better than that of the benchmark model.

System characteristics
Classifier AE, PixelSNAIL, VQ-VAE, normalizing flow
System complexity 10931697, 269992
Acoustic features log-mel energies
Data augmentation mixup
Decision making average
Subsystem count 2
Front end system HPSS
PDF

A DUAL-STREAM CNN WITH SUB-CLUSTER ADAPTIVE COSINE LOSS FOR ANOMALOUS SOUND DETECTION

H_ M_nh D_ng
Faculty of Information Technology 1, Posts and Telecommunications Institute of Technology, Ha Noi, Viet Nam

Abstract

This report describes our system for the DCASE 2025 Challenge Task 2: "Unsupervised Anomalous Sound Detection for Machine Condition Monitoring" [1]. Our approach is based on a dual-stream Convolutional Neural Network (CNN) architecture designed to extract robust features from raw audio signals. One stream processes frequency characteristics via a Fast Fourier Transform (FFT), while the second stream analyzes time-frequency features from a magnitude spectrogram. To enhance model generalization, we employ two data augmentation techniques: Mixup [2] and SpecAugment [3]. The core of our system is a metric learning approach using the Sub-Cluster AdaCos (SCAdaCos) loss function, inspired by AdaCos [4], to learn highly discriminative embeddings. Anomaly scores are calculated based on the cosine similarity between test sample embeddings and pre-computed class centroids from the training data. Our results on the development set show that the system has a foundational capability for anomaly detection, with performance metrics surpassing the random guess baseline.

System characteristics
Classifier CNN, Ensemble
System complexity 269992
Acoustic features FFT, Magnitude Spectrogram
Data augmentation Mixup, SpecAugment, Random Crop/Padding
Decision making average
Subsystem count 2
PDF

JOINT DOMAIN-ADVERSARIAL AND CONTRASTIVE LATENT OPTIMIZATION FOR UNSUPERVISED AUDIO ANOMALY DETECTION

Taharim Rahman Anon, Jakaria Islam Emon
Hokkaido Denshikiki Co., Ltd., Sapporo, Hokkaido, Japan

Abstract

This paper presents a unified framework for Unsupervised Anomaly Sound Detection (UASD) that combines Convolutional Autoencoders (CAE) with Domain-Adversarial Neural Networks (DANN) and Deep Support Vector Data Description (Deep SVDD). Our approach addresses the critical challenges of domain shift and first-shot generalization in the DCASE 2025 Task 2 challenge. The proposed architecture employs a CAE to learn compact latent representations while a domain classifier with gradient reversal enforces domain-invariant features. The latent space is simultaneously optimized using Deep SVDD to create a tight hypersphere around normal samples. Unlike traditional reconstruction-based methods, our approach leverages both reconstruction loss and a contrastive SVDD loss that pushes generated pseudo-outliers from the normal data boundary, combined with adversarial domain adaptation. Our system demonstrates superior performance over the DCASE 2025 autoencoder baseline, with achieving a total score of 0.77 (versus baseline 0.65). The domain-adversarial training significantly improves target domain generalization, establishing the efficacy of joint optimization for robust anomaly detection in dynamic acoustic environments.

System characteristics
Classifier AE, Deep SVDD, GRL
System complexity 17040000
Acoustic features log-mel energies
Data augmentation Synthetic Anomaly Augmentation, noise bursts, frequency shifts
PDF

ENHANCED UNSUPERVISED ANOMALOUS SOUND DETECTION VIA CONVTASNET-BASED SEPARATION AND CONDITIONAL AUTOENCODING

Chenjun Fu, Ronghuan Zhao, Qiang Wang, Hao Wu, Liang Zou
China University of Mining and Technology, XuZhou,China

Abstract

This report outlines our approach to first-shot unsupervised anomalous detection for machine condition monitoring, developed for DCASE 2025 Task 2. Given the constraint of only having normal operational data and the availability of clean target device sounds or background noise, our method focuses on leveraging audio separation and a self-supervised AutoEncoder (AE) for anomaly detection. Key components of our approach include training an audio separation module to extract target sounds for effective denoising and data augmentation, encoding audio features via an AutoEncoder trained solely on normal data, and performing conditional modeling with attribute and domain labels to enhance generalization to unknown domains and complex acoustic environments. Anomalies are detected using a K-Nearest Neighbors (KNN)-based method by measuring the distance between each test sample and its nearest neighbors in the training set; greater distances imply higher anomaly likelihood. Our approach achieved notable performance on the development set, demonstrating is effectiveness. The AUC for the target domain was 64.1% and for the source domain was 60.8%. Addtitionally, the Partial AUC values (p=0.1) for the target and source domain was 55.6 % . These results underscore the robustness and applicability of our methodology

System characteristics
Classifier KNN
Acoustic features log-mel energies
Decision making minmum
Front end system sound separation
PDF

The NU systems for DCASE 2025 Challenge Task 2

Takuya Fujimura, Ibuki Kuroyanagi, Tomoki Toda
Nagoya University, Nagoya, Japan

Abstract

In this report, we present our anomalous sound detection (ASD) systems developed for DCASE 2025 Challenge Task 2. We propose a cascaded approach that integrates a target signal enhancement (TSE) model with a discriminative ASD system. First, we train the TSE model utilizing supplementary clean machine sounds and noise data. Then, we train the discriminative ASD system using the enhanced machine sounds to improve noise robustness. To further improve detection performance, we incorporate recently proposed techniques into the discriminative ASD system: multi-resolution spectrograms, pre-trained self-supervised learning features, and pseudo-label generation. Our final ensemble system has achieved 64.91% in the official scores calculated as a harmonic mean of the area under the curve (AUC) and partial AUC (p= 0.1) over all machine types and domains in the development set.

System characteristics
Classifier CNN
System complexity 1502700000, 2383200000, 3804300000, 4955100000
Acoustic features spectrogram, spectrum
Data augmentation mixup
Decision making maximum
System embeddings BEATs, EAT, SSLAM
Subsystem count 19, 32, 51, 67
External data usage pre-trained model, training of enhancement model
Front end system DNN-based Enhancement
PDF

Anomalous Sound Detection Using Pre-trained Model With Statistical Feature Difference Representation

Shiheng Zhang, Feiyang Xiao, Shitong Fan, Qiaoxi Zhu, Wenwu Wang, and Jian Guan
College of Computer Science and Technology, Harbin Engineering University, Harbin, China and Ultimo, Australia and Centre for Vision, Speech and Signal Processing (CVSSP), Guildford, UK and College of Computer Science and Technology, Harbin, China

Abstract

This report presents GISP-HEU’s submission for Task 2 of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2025 Challenge. The submission utilises pre-trained models for feature extraction to obtain refined audio representations. In addition, a statistical weight is formulated based on the differences in audio features between the test and training samples. This weight is applied during the testing phase to enhance the distinction between normal and anomalous audio. The submission comprises four individual systems. System 1 utilises BEATs alongside the statistical feature difference weighting. System 2 builds on System 1 by incorporating clean and noisy data during training. System 3 employs AnoPatch and uses development data spanning DCASE 2022 to DCASE 2025. Finally, System 4 is an ensemble of the previous three systems.

System characteristics
Classifier KNN
System complexity 300000000
Acoustic features log-mel energies
PDF

XJU System for First-Shot Unsupervised Anomalous Sound Detection

Shun Huang, Liang He
School of Computer Science and Technology, Xinjiang University, Urumqi, China and Department of Electronic Engineering, Tsinghua University, Beijing, China

Abstract

Previous studies have shown that using large-scale audio pre-training models for anomaly sound detection under domain shift scenarios has demonstrated significant promise. In this year’s competition, compared to last year, supplementary sets have been added. Due to our lack of understanding in denoising, this dataset was not utilized throughout the training process. In this technical report, we continue to fine-tune large pre-training models, employing subcenter arcface for training, primarily using the BEATs and EAT models. We trained only on the current development set and additional supplementary sets, achieving a score of 64.46% on the development set.

System characteristics
Classifier CNN
System complexity 172.92M, 176.35M, 87.22M, 91.70M
Acoustic features log-mel energies, spectrum
Data augmentation mixup, specaug
Decision making maximum
System embeddings BEATs, BEATs, EAT, EAT
External data usage pre-trained model
PDF

THUEE SYSTEM FOR DCASE 2025 ANOMALOUS SOUND DETECTION CHALLENGE

Anbai Jiang, Wenrui Liang, Shi Feng, Yihong Qiu, Yixiang Zhao, Junjie Li, Pingyi Fan, Wei-Qiang Zhang, Cheng Lu, Xie Chen, Yanmin Qian, Jia Liu
Department of Electronic Engineering, Tsinghua University, Beijing, China and Schools of Economy, North China Electric Power University, Beijing, China and Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China

Abstract

This technical report presents the THUEE system for the DCASE 2025 anomalous sound detection (ASD) challenge. Motivated by the success of self-supervised learning (SSL) and generative modeling in various modalities and tasks, we build the system by first adapting multiple SSL pre-trained models for ASD. We find that fine-tuning the model with all six DCASE ASD datasets significantly boosts the ASD performance. To address granularity mismatches in machine attributes, we adopt an adaptive prototype modeling scheme. Furthermore, we leverage powerful diffusion-based audio generation models to synthesize samples under minor working conditions, augmenting the imbalanced training set to mitigate domain gaps between source and target distributions. Finally, we conduct mega ensembling of dozens of single models by Bayesian optimization, achieving substantial performance gains. The best ensemble system reaches 74.29% on the DCASE23 dataset, 70.17% on the DCASE24 dataset and 69.35% on the DCASE25 development set.

System characteristics
Classifier diffusion, ensemble, pre-trained models
System complexity 1.3B, 3.5B, 3B, 7B
Acoustic features STFT, fbank
Data augmentation specaug
Decision making median
Subsystem count 15, 34, 38, 74
External data usage Audioset, Freesound, MTG-Jamendo, Music4all, BEATs, EAT, Audioset, Freesound, MTG-Jamendo, Music4all, BEATs, EAT, Tangoflux
PDF

AISTAT LAB SYSTEM FOR FIRST-SHOT UNSUPERVISED ANOMALOUS SOUND DETECTION

Hyun Jun Kim, Min Jun Kim, Hyeon Gyu Bae, Changwon Lim
Applied Statistics, Chung-Ang University, Seoul, Korea

Abstract

This report addresses the AISTAT team’s submission to First-Shot Unsupervised Anomalous Sound Detection task in DCASE2025 Task 2. Unlike the previous years’ challenges, the available training data spans from the training dataset of 2020 to 2025. To effectively learn from the given data, we adopt a two-stage training strategy consisting of pretraining followed by transfer learning. During the transfer learning stage, pseudo-labeling is applied to data without attribute information to assign approximate labels and enhance model adaptation. Also, ArcFace loss and Center loss are employed together to directly reduce class-intra variance. Additionally, to extract more informative audio representations, we leverage the multi-layer aggregation. Through these techniques, our single best model achieved a harmonic mean of 66.12, while our best ensemble model achieved a harmonic mean of 66.78.

System characteristics
Classifier k-means
System complexity 132800000, 199200000, 66400000
Acoustic features log-mel spectrogram
Data augmentation specaug
Decision making weighted average
System embeddings BEATs, EAT
Subsystem count 6
External data usage pre-training
PDF

Metadata-Free Text-to-Audio Normal Synthesis and Latent Gradient Perturbation for Unsupervised Anomalous Sound Detection

JeongSik Kim, JongWoo Sung, HyoenJun Bae, SukHwan Lee
Computer Engineering, Dong-A University, Busan, South Korea and Dong-A University, Busan, South Korea

Abstract

This technical report shows a fully metadata-free framework for unsupervised anomalous sound detection that synthesizes both normal and anomalous training examples. First, we generate diverse normal audio clips by training and adapting a pretrained Tango text-to-audio model: we apply LoRA and fine-tune Text Encoder and VAE in Tango, and full tuning UNet using three automated prompt strategies (fixed templates, spectrogram-statistic descriptions, and CLAP-filtered captions). Next, we create realistic anomalous spectrograms by perturbing encoded normal representations with gradient ascent and enforcing their magnitude via truncated projection. These synthetic normal and anomalous samples are then used to train a downstream spectrogram-based detector, yielding marked improvements in detection accuracy. In future work, we will close the gap between synthetic and real distributions and extend our approach to direct anomalous audio generation.

System characteristics
Classifier AE, CNN, Gradient adcent, LDM, VAE
System complexity 1326044274, 568462912
Acoustic features Linear Spectrogram, STFT
Data augmentation Tango, Audio Flamingo 2
External data usage Tango, Audio Flamingo 2, LAION-CLAP
PDF

FIRST-SHOT UNSUPERVISED ANOMALOUS SOUND DETECTION WITH FINE-TUNED HUBERT AND K-NEAREST NEIGHBORS

Meghan Kret
Albert Nerkin School of Engineering, Dept. of Electrical Engineering, The Cooper Union, New York, NY, USA

Abstract

We present a lightweight first-shot anomalous-sound-detection (ASD) system for DCASE 2025 Task 2. The method couples a HuBERT-Base backbone―pre-trained on AudioSet at 16 kHz―with a non-parametric k-nearest-neighbor detector in embedding space. Only normal clips from the development and evaluation “train” partitions are required; no synthetic anomalies are generated. A single forward pass extracts a frame-level feature tensor.

System characteristics
Classifier k-NN
Acoustic features raw waveform
Data augmentation none
System embeddings HuBERT
External data usage pre-trained model
PDF

First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring

Zongmu Lin, Yihao meng, Yuanhang Qian, Yuankai Zhang, Yujie Zhu, Gongping Huang
International Acoustic Signal Processing Laboratory, Wuhan University, Hubei , China and Wuhan University, Hubei , China

Abstract

Automatic detection of machine anomaly remains challenging for machine learning. Unsupervised models have been widely applied in lots of scenarios successfully. This technical report outlines our solutions to Task 2 of the DCASE2025 challenge.The objective is to detect audio recording containing anomalous machine sounds in a test set, when the training dataset itself does not contain any examples of anomalies. Our approaches are based on transformer auto-encoder model and use pretrained model to extract the multi-scale features.

System characteristics
Classifier AE
System complexity 17149084, 493651
Acoustic features log-mel energies
System embeddings HTS-AT
External data usage pre-trained model
PDF

SUBMISSION FOR THE DCASE2025 TASK2: ROBUST ANOMALY SOUND DETECTION VIA BSS-AUGMENTED PRE-TRAINED MODEL FINE-TUNING

Haifeng Xu, Yizhou Tan , Shengchen Li
Anhui University of Science and Technology., Huainan, China and Xi’an Jiaotong-Liverpool University, Suzhou, China

Abstract

Anomaly Sound Detection (ASD) is crucial for predictive maintenance in industrial settings, yet its performance is often severely constrained by high-intensity, non-stationary background noise. To address this challenge, this paper proposes a robust ASD framework incorporating multi-source data fusion and fine-tuning. Specifically, we fuse machine sounds recorded in factories (containing only normal samples) with easily available clean mechanical sounds or environmental noise data. A pretrained BEATs model serves as the feature extractor. To enhance noise robustness, we innovatively introduce a Blind Source Separation (BSS) decoder as an auxiliary task atop the BEATs encoder. This guides the model in learning feature representations that are resistant to noise interference by minimizing BSS loss. Experiments conducted on the DCASE 2025 Development dataset demonstrate that our method significantly outperforms baseline approaches, achieving AUC values of 79.86% and 71.47% on ToyCar and ToyTrain, respectively. This represents relative improvements of 6.69% and 9.71% over baseline systems, underscoring the efficacy of our proposed framework in acoustic event detection and classification scenarios.

System characteristics
Classifier KNN
Acoustic features raw waveform
Data augmentation mixup
Decision making average
System embeddings BEATs
PDF

SVD DECOMPOSITION WITH AUTOENCODERS FOR DCASE 2025 TASK 2

Vladimir Igoshin, Vsevolod Kleshchenko, Dmitry Chirkov, Mark Mirolyubov, Mihail Petrov, Igor Lobanov
School of Physics and Engineering, ITMO University, Saint Petersburg, Russia

Abstract

In this work, we address the problem of single-channel sound anomaly detection by leveraging Singular Value Decomposition (SVD) as a feature extraction and dimensionality reduction technique. Specifically, we apply SVD across the entire dataset of spectrograms and retain only a limited number of dominant components to represent the input signals in a compact latent space. We evaluate two autoencoder-based models on the reduced representations. First one is a challenge baseline autoencoder trained on the low-dimensional features obtained from SVD. Second is transformer-inspired autoencoder that integrates a convolution layer and an attention mechanism to better capture temporal structures indicative of anomalous behavior.

System characteristics
Classifier AE
System complexity 144568, 25216
Acoustic features spectrogram
Front end system SVD
PDF

ANOMALOUS SOUND DETECTION METHOD USING CONTRASTIVE LEARNING

Kosei Ozeki, Takeru Shiraga, Takahiko Masuzaki, Nobuaki Tanaka, and Toshiyuki Kuriyama
Artificial Intelligence R&D Dept., Mitsubishi Electric Corporation, Kanagawa, Japan and Mitsubishi Electric Corporation, Kanagawa, Japan

Abstract

This paper presents methods for anomalous sound detection for DCASE2025 Task 2. The goal of this contest is to identify whether the sounds emitted from target machines are normal or anomaly. We implemented the following approaches: 1. Anomaly detection using a pre-trained model directly. 2. Fine-tuning the DCASE general model learned in Stage1 for individual machines. 3. Implementing the flow of approach 2 with data augmentation using additional data (clean machine data or noise-only data). 4. Performing sound source separation of operation sounds and noise, followed by implementing the flows of approaches 1 or 2. As a result, our approach achieved higher accuracy compared to the baseline method in the evaluation of the development dataset.

System characteristics
Classifier Contrastive learning based on the SimSiam framework, kNN
System complexity 85253504
Acoustic features Mel spectrogram
Data augmentation Gain adjustment, Polarity Inversion, Pitch Shifting, Time Stretching, Additive Background Noise
System embeddings CED
External data usage pre-trained model, embeddings, data augmentation
Front end system Normalization, Patchification
PDF

Anomaly Sound Detection Method Based on Training Attribute Classification Models

Fan Chu, Mengui Qian
National Intelligent Voice Innovation Center, Hefei, China

Abstract

In this report, we present our solution to the DCASE 2025 Challenge Task 2, focusing on First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring. In this year's challenge, some machines still lack attribute and domain labels, while clean machine sound or background noise are provided. Our approach involves using clustering or feature frequency analysis algorithms to assign artificial labels to samples without attribute labels, then training an attribute classification model together with other machines that have attributes. Additionally, we introduce a data augmentation strategy by mixing clean machine sound with background noise to generate simulated data. Finally, we employ the model's embedding to train a KNN model for obtaining anomaly scores. Our system achieves 63.25% in the harmonic mean of AUC and pAUC (p = 0.1) across all machine types and domains on the development set.

System characteristics
Classifier KNN
System complexity 10M
Acoustic features log-mel energies, spectrogram
Data augmentation mixup
PDF

GENREP FOR FIRST-SHOT UNSUPERVISED ANOMALOUS SOUND DETECTION OF DCASE 2025 CHALLENGE

Phurich Saengthong, Takahiro Shinozaki
Information and Communications Engineering, Institute of Science Tokyo, Japan and Institute of Science Tokyo, Japan

Abstract

Recent advances in large-scale pre-trained audio models have shown that frozen embeddings can provide robust and transferable representations for general audio tasks. Building on GenRep, which uses frozen embeddings with k-nearest neighbors and domain-wise Z-score normalization for anomaly detection under domain shift, we extend this approach by exploring several directions, including normalization strategies, model scaling, and feature ensembling. First, we study alternative normalization methods such as global Z-score normalization, local density normalization, and domain-wise local density normalization. Second, we evaluate pre-trained audio encoders ranging from 5M to 300M parameters on the DCASE2025 Task 2 dataset to examine the impact of model scale. Third, we study the effect of ensemble fusion using features from multiple frozen encoders. Our results indicate that even the smallest pre-trained encoder (5.49M) can outperform a baseline autoencoder, and that larger models and ensembling contribute to further improvements without updating model parameters. The code is available open-source.

System characteristics
Classifier ensemble
System complexity 5490300, 569284800
Acoustic features log-mel energies
Decision making average
System embeddings BEATs, M2D-CLAP, EAT, SSLAM, CED
Subsystem count 5
PDF

Distance-Based Unsupervised Anomalous Sound Detection with Attentive Statistics Pooling and ArcFace Multi-Task Learning

Masayuki Sera, Takao Kawamura, Nobutaka Ono
computer science, Tokyo Metropolitan University, Tokyo, Japan and Tokyo Metropolitan University, Tokyo, Japan

Abstract

In this technical report, we describe our submission to the DCASE 2025 Challenge Task 2, titled “First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring.” Our system is a distance-based anomalous sound detection method that determines whether a test input is normal or anomalous based on the Euclidean distance to embeddings of normal data. To obtain effective embeddings, we first apply the pretrained acoustic model BEATs to the input audio clip without any fine-tuning. The resulting patch-level features are then aggregated using Attentive Statistics Pooling to form a fixed-dimensional representation. To further improve the embeddings, we employ AcrFace-based multi-task learning with machine type and attribute classification objectives, which are used only during training. Our system achieved an Ω score of 0.6132 on the official development dataset, corresponding to a 5.3 percentage point improvement over the baseline system (0.5599).

System characteristics
Classifier ArcFace, Multi-task learning
System complexity 90,409,441.0
Acoustic features log-mel energies
System embeddings BEATs
PDF

Patch-Based Contrastive Learning With Latent Space Clustering For Unsupervised Sound Anomaly Detection

Abhivanth Sivaprakash, K Krish Sundaresh, Ankith Vijayyan, Adhithya Srivatsan, Chandrakala S
Computer Science Engineering, Shiv Nadar University, Chennai, Chennai, India

Abstract

This report presents our submission for the DCASE 2025 Challenge Task 2 on first-shot unsupervised anomalous sound detection. We propose a contrastive learning-based framework designed to capture fine-grained patterns from spectrogram representations while adapting to both attribute-rich and attribute-absent machine conditions. The method leverages local feature learning and selectively integrates auxiliary metadata to enhance generalization under domain shifts. Training is performed jointly across all machine types using only normal data. Anomaly scoring is carried out in a learned embedding space using a statistical distance-based method. Our approach outperforms official baselines in both source and target domains on the development dataset, demonstrating strong potential for robust and flexible industrial anomaly detection.

System characteristics
Classifier contrastive learning
System complexity 21469992
Acoustic features log-mel energies
Data augmentation RandomResizedCrop, RandomHorizontalFlip, ColorJitter, RandomGrayscale
PDF

PRE-TRAINED MODEL ENHANCED ANOMALOUS SOUND DETECTION SYSTEM FOR DCASE2025 TASK2

Lei Wang
individual, individual, Fuyang, China

Abstract

This study proposes a robust approach to address DCASE2025 Challenge Task 2, focusing on First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring. The task presents a unique challenge of training models with and without attribute information, necessitating robust performance under both scenarios. To address this challenge, we utilize advanced pre-trained models as the feature extraction backbone, integrate attribute classification and domain classification networks, and fine-tune them on the DCASE2025 Task2 dataset. Finally, we employ a KNN model as the backend for calculating anomaly scores. Benefiting from the powerful feature extraction capability of the pre-trained model, our system achieves a competitive harmonic mean of AUC and PAUC(p = 0.1) of 60.9% on the development set.

System characteristics
Classifier EAT
System complexity 87M
Acoustic features log-mel energies
PDF

FINE-TUNING PRE-TRAINED AUDIO MODELS FOR ANOMALOUS SOUND DETECTION

Junjie Wang

Abstract

This technical report presents our solution to Task 2 of the DCASE 2025 Challenge, which focuses on unsupervised anomalous sound detection for machine condition monitoring. We developed four subsystems, all of which detect anomalies by extracting embeddings and applying outlier detection algorithms. Among them, three systems utilize fine-tuned audio pre-trained models for embedding extraction, while the remaining one employs a convolutional neural network. Unlike previous approaches that classify machine meta-data, our system enhances domain generalization by training models to distinguish between machine sounds and background noise.

System characteristics
Classifier k-means
System complexity 0.6B, 3M, 90M
Acoustic features log-mel energies
Data augmentation mixup, mixup, specaug
System embeddings BEATs, Dasheng
PDF

FIRST-SHOT UNSUPERVISED ANOMALOUS SOUND DETECTION BASED ON FUSION OF CNN-AE AND BEATs-KNN

Wang Xiaoliang, Ming Ao
Zhejiang University, Hangzhou, China

Abstract

This technical report presents our submission to the DCASE 2025 Challenge Task 2. We propose a fusion-based system combining a CNN-BiGRU-Attention Autoencoder with a BEATs-KNN model to improve unsupervised anomalous sound detection (ASD). Both models are independently trained and then combined at the score level using a weighted average strategy. The fusion weights are optimized using the development dataset. Results show that this hybrid approach improves the robustness of anomaly detection across multiple machine types. Through the fusion of various models and methods, we have achieved a hmean of 66.00% on the development dataset.

System characteristics
Classifier AE, BEATs, BiGRU, CNN
System complexity 269992
Acoustic features log-mel energies
PDF

First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring Based on Ensemble Learning and Domain Generalization

Ting Wu, Lu Han, Zhaoli Yan, Xiaobin Cheng, Jian Wen, Jun Yang
State Key Laboratory of Acoustics and Marine Information, The Institute of Acoustics of the Chinese Academy of Sciences, Beijing, China and The Institute of Acoustics of the Chinese Academy of Sciences, Beijing, China and Beijing University of Chemical Technology, Beijing, China

Abstract

Unsupervised pretrained models have achieved remarkable success across a wide range of applications. In this report, an approach is presented for DCASE 2025 Task 2: First-shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring. To address this challenge, an anomaly detection algorithm is proposed, which combines density estimation with cross-domain interpolation to robustly detect anomalies. Additionally, a two-stage pretraining strategy within a teacher-student framework is adopted to enhance audio data representation. A dual-headed network architecture is developed to leverage both labeled and unlabeled loss functions, mitigating the scarcity of labeled data. Finally, to optimize the ensemble of several large-scale models, an adaptive weighted combination perturbation search algorithm is introduced to determine the optimal fusion weights. Collectively, these methods achieve a score of 69.94% on the official development dataset, significantly surpassing the baseline model.

System characteristics
Classifier ResNet, ensemble
System complexity 28592295
Acoustic features log-mel energies
System embeddings BEATs, EAT, SSLAM
PDF

A TWO STAGE FUSION ANOMALY DETECTION APPROACH FOR TASK2

Jie Yang
Shanghai, China

Abstract

This technical report details our approach to addressing Task 2 of the DCASE 2025 Challenge. We propose a two stage fusion adaptive anomaly detection scheme which combine adaptive filtering for denoising and separation and neural network-based classifier. First, traditional signal separation and denoising techniques are employed to preprocess the raw audio signal. This stage focuses on suppressing noise, isolating interfering sound sources, and enhancing the signal-to-noise ratio (SNR) of the target machine sound. For the attribute classification network, we leverage the depth-wise separable convolutions and bottleneck structure of MobileFaceNet to efficiently learn deep discriminative features of anomalous sounds. Finally,an anomaly score is computed based on K-Nearest Neighbors (KNN). The results demonstrate that the proposed method achieves significant performance improvements and ensures robust adaptability under varying data conditions. Furthermore, the fraframework's flexibility in handling different types of input data enhances its applicability in real-world industrial machine monitoring scenarios.

System characteristics
Classifier AE
System complexity 1M
Acoustic features log-mel energies
PDF

Enhancing Machine Sound Anomaly Detection via Source Separation and Hybrid SSL Fusion

Yucong Zhang, Zhang Chen, Ming Li
Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Suzhou, China

Abstract

This technical report presents our solution for DCASE 2025 Task 2: Anomalous Sound Detection for Machine Condition Monitoring. Our approach integrates BEATs and AudioMAE models through two fusion strategies: 1) score-level ensemble of independently fine-tuned models, and 2) feature-level fusion with unified attentive statistical pooling. Both models employ LoRA-based adaptation on combined historical and current DCASE datasets, enhanced by source separation for clean-referenced machines and universal noise augmentation. The anomaly detection mechanism leverages prototype embeddings generated from KMeans clustering and target samples. Achieving a 66.34% average AUC/pAUC score on the development set, our system demonstrates 10.47% improvement over the baseline, highlighting the effectiveness of hybrid fusion strategies in capturing diverse normal sound patterns.

System characteristics
Classifier AE, ensemble, transformer
System complexity 176.33 M, 176.71 M, 177.31 M, 85.23 M
Acoustic features log-mel energies, raw waveform
Data augmentation noise augmentation, noise augmentation, spectral augmentation
Decision making average
System embeddings BEATs
Subsystem count 2, 3
External data usage simulation of attribute labels, pre-trained model
PDF

FUSION SYSTEM FOR FIRST-SHOT UNSUPERVISED ANOMALOUS SOUND DETECTION FOR MACHINE CONDITION MONITORING

Zhe Cao, Jichao Zhang, Xiao-Lei Zhang, Chi Zhang, Xuelong Li
School of Marine Science and Technology, Northwestern Polytechnical University, Xian, China and School of Marine Science and Technology; Institute of Artificial Intelligence (TeleAI), Northwestern Polytechnical University; China Telecom, Xian, China; Shanghai, China and Institute of Artificial Intelligence (TeleAI), China Telecom, Shanghai, China

Abstract

The DCASE 2025 Challenge Task 2 focuses on first-shot unsupervised anomalous sound detection, where the main challenges include domain shift, generalization issues, and the absence of attribute information. To address these problems, we leverage the newly introduced past-year DECASE Challenge Task 2 datasets and the Audioset for model pre-training to extract audio features. In this work, we employ LoRA fine-tuning, dual-branch feature exchange, and multi-layer feature fusion methods. In addition, data augmentation is utilized to mitigate domain shift, and multiple models are fused to further enhance performance. As a result, an hmean of 67.27% is achieved on the development dataset.

System characteristics
Classifier ensemble, knn, normalizing flow, transformer
System complexity 408,731,805, 408731805
Acoustic features fbank
Data augmentation SMOTE
Decision making weighted average
System embeddings BEATs, EAT
Subsystem count 6
External data usage pre-trained model
PDF

Multi-Modal Acoustic Anomaly Detection via Reconstruction and Discriminative Learning with BEATs Representations

Pengyuan Zhao, Zulong Yan, Tianju Zhao, Yutao Zhang, Meng Lei
School of Information and Control Engineering, Xuzhou, CN

Abstract

This technical report focuses on anomalous sound detection (ASD) in DCASE 2025 Task 2, we propose two deep learning approaches based on multimodal feature fusion to enhance robustness and generalization across domains. In the data preparation stage, in order to solve the problem of data complexity, this paper separates the pure sound events and background noise provided by the organizer based on TF-Locoformer, and constructs a more robust data set for model training by reconstructing diversified training samples through random combination. The first approach extracts frame-level waveform features using a fine-tuned BEATs model and aligns them with Mel-spectrogram features extracted by MobileFaceNet. These are fused and passed into an ArcFace classifier for joint attribute and domain classification, enabling discriminative learning and multi-task optimization. The second approach introduces a multimodal autoencoder architecture combining BEATs and TgramNet for hierarchical feature extraction, jointly trained with reconstruction and classification losses. Our best model achieves a pAUC of 0.59.56 on the validation set, demonstrating strong detection performance under multi-source and complex background conditions.highlighting the effectiveness and potential of the proposed methods in real- world, multi-domain ASD scenarios.

System characteristics
Classifier AENet, MobileFaceNet
System complexity 269992, 368432
Acoustic features log-mel energies
Data augmentation specaug
System embeddings BEATs
PDF

SJTU-AITHU System for DCASE 2025 Anomalous Sound Detection Challenge

Xinhu Zheng, Anbai Jiang, Bing Han, Shuwei Zhang, Wei-Qiang Zhang, Xie Chen, Cheng Lu, Pingyi Fan, Jia Liu, Yanmin Qian
Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China and Tsinghua University, Beijing, China and Algorithm Group, Huakong AI Plus Company Limited, Beijing, China and Department of Electronic Engineering, Tsinghua University, Beijing, China and Schools of Economy, North China Electric Power University, Beijing, China

Abstract

This report presents our solutions for DCASE 2025 Task 2: First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring. In this domain, pre-trained models have demonstrated considerable potential, particularly in handling domain shifts. We develop our systems based on BEATs and the EAT family and explore various training strategies to enhance performance. Sub-center loss and noise-aware training are employed to improve system performance. By fusing various models and methods, we achieve an hmean of 69.12% on the development dataset.

System characteristics
Classifier ensemble, pre-trained models
System complexity 2B, 3B, 4.6B
Acoustic features STFT, fbank
Data augmentation specaug, add noise
Decision making median
Subsystem count 21, 36, 51
External data usage Audioset, Freesound, MTG-Jamendo, Music4all, BEATs, EAT
PDF

ENHANCED ANOMALY DETECTION APPROACH FOR DCASE 2025 TASK 2

Guirui Zhong, Qing Wang, Jun Du
University of Science and Technology of China, Hefei, China

Abstract

Addressing the unique challenge of the DCASE 2025 Task 2, where the availability of clean machine and noise-only data varies and datasets in previous years are introduced, we propose an enhanced anomaly detection approach that combines data augmentation and two-stage pre-training methods using pre-trained audio separation and self-supervised learning (SSL) models, respectively. Leveraging audio separation models guided by clean machine or noise-only data, our system can separate clean data from noisy data and generate more diverse data in the training phase. Using a lot of machine sound data for two-stage pre-training, the system can better adapt to anomalous sound detection (ASD) task in the downstream fine-tuning task. By integrating these approaches, our system achieves a better performance across different machines on the DCASE 2025 ASD development dataset, ensuring reliable anomaly detection in machine condition monitoring applications.

System characteristics
Classifier KNN
System complexity 87M
Acoustic features log-mel energies
Data augmentation mixup, addnoise
Decision making average
Subsystem count 2
External data usage embeddings, pre-trained model
Front end system sound separation
PDF

MACHINE ANOMALOUS SOUND DETECTION COMBINING CONVOLUTIONAL AUTO-ENCODER AND CONTRASTIVE LEARNING

Qing Zhou, Sai Wu
College of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an, China and Xi'an University of Architecture and Technology, Xi'an, China

Abstract

Machine anomalous sound detection (MASD) under noisy industrial conditions remains challenging due to limited anomalous samples, background noise interference, and domain shift. This paper proposes a multi-task learning framework combining a semi-supervised convolutional auto-encoder (CAE) with self-supervised classification and contrastive learning to address these issues. The core architecture uses a CAE backbone and the encoder output is projected into an audio embedding vector which is later fed into a linear classifier for self-supervised attribute classification (e.g., domain, operational parameters). Crucially, the framework leverages newly available clean machine data and noise-only data through a contrastive loss term. This loss pulls embeddings of noisy and clean machine samples of the same class closer while pushing those of noisy machine samples away from pure noise samples, enhancing noise robustness. The model is optimized jointly with a combined loss function integrating reconstruction, classification, and contrastive objectives. During inference, reconstruction errors and audio embeddings are concatenated as input features for a domain-aware anomaly detector. Evaluated on the DCASE2025 Task 2 dataset, the proposed method achieves a harmonic mean score of 63.80%, significantly outperforming the baseline. Ablation studies confirm each component’s contribution, demonstrating the effectiveness of the multi-task strategy in learning discriminative and noise-invariant representations for MASD.

System characteristics
Classifier AE, KNN, LOF
System complexity 194881
Acoustic features log-mel energies
Data augmentation mixup, specaug, mixup, specaug, smote
PDF

AN EFFICIENCE ANOMALOUS SOUND DETECTION SYSTEM FOR DCASE 2025 TASK 2

Wentao Zhou, Ying Hu, Xin Fan, Nannan Teng, Tianqing Zhou, Fangxu Chen, Qingjing Wan, Qiong Wu, Qin Yang
Key Laboratory of Signal Detection and Processing in Xinjiang, XinJiang University, Urumqi, China and XinJiang University, Urumqi, China

Abstract

This technical report describes the system we submitted to DCASE 2025 Challenge Task 2: First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring.This year’s tasks are fundamentally aligned with those of last year. To reflect practical application scenarios, machine attributes are not always fully known. Building upon this, additional clean machine data or noise-only data have been incorporated into the training set. Our system employs the pre-trained model BEATs, utilizing the LoRA finetuning approach for the anomalous sound detection task. Arcface loss is incorporated to constrain machines with unknown attributes. Our best system achieved a harmonic mean of 77.13% in the harmonic mean of AUC in the source domain, 56.07% in AUC in the target domain, and 57.72% in pAUC(p=0.1) on the development set.

System characteristics
Classifier Arcface, KNN
System complexity 90 M
Acoustic features log-mel spectrogram
Data augmentation specaug
System embeddings BEATs
External data usage BEATs
PDF