First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring


Challenge results
We have released the ground truth labels and evaluator for the evaluation dataset. More detailed information on the ground truth labels and the evaluator can be found in the task description page.

Task description

The goal of this task is to identify whether a machine is normal or anomalous using only normal sound data under domain shifted conditions. Our task in 2023 was also focused on the first-shot problem and domain generalization, which was realized by providing completely different machine types for the development and evaluation dataset with additional attribute information (such as the machine operation speed) attached to them. Our task in 2024 will also be held with the development and evaluation dataset having different machine types, whereas for the evaluation dataset, the machine types will be new ones not seen in our previous tasks. In addition, we will conceal additional attribute information for at least one machine type in the development dataset, which also mimics some real-world situations. The participants are expected to develop techniques that can be useful for solving the first-shot problem and train models robust to 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
3DPrinter
(AUC)
3DPrinter
(pAUC)
AirCompressor
(AUC)
AirCompressor
(pAUC)
BrushlessMotor
(AUC)
BrushlessMotor
(pAUC)
HairDryer
(AUC)
HairDryer
(pAUC)
HoveringDrone
(AUC)
HoveringDrone
(pAUC)
RoboticArm
(AUC)
RoboticArm
(pAUC)
Scanner
(AUC)
Scanner
(pAUC)
ToothBrush
(AUC)
ToothBrush
(pAUC)
ToyCircuit
(AUC)
ToyCircuit
(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)
DCASE2024_baseline_task2_MSE DCASE2024baseline2024 39 56.50830191796572 ± 0.001050516938082758 59.72 49.42 55.38 55.47 66.92 55.58 52.89 51.63 58.11 50.21 50.96 51.16 60.48 50.11 72.15 52.74 62.41 50.00 50.37 48.77 61.77 47.95 61.70 57.58 61.47 57.53 69.87 55.65 61.26 51.77 48.66 52.42
Wilkinghoff_FKIE_task2_1 WilkinghoffFKIE2024 62 52.46265926819839 ± 0.0010707667655151189 67.11 58.74 53.56 48.63 47.76 50.68 57.02 56.32 43.14 53.26 67.81 58.11 58.67 49.16 41.68 52.00 48.59 48.00 50.45 49.40 60.65 53.50 68.60 58.80 75.10 59.50 72.55 54.80 86.25 65.60 77.30 68.30
Fujimura_NU_task2_1 FujimuraNU2024 26 58.89866752033418 ± 0.001041273079131894 73.17 59.79 60.48 49.05 56.59 50.53 65.50 52.68 66.39 53.16 70.58 57.68 60.86 50.37 71.18 56.11 47.10 48.68 54.41 49.84 75.94 59.74 75.75 61.16 63.17 56.68 72.28 54.53 93.24 80.37 78.61 69.16
Zhao_CUMT_task2_1 ZhaoCUMT2024 9 61.96515488201288 ± 0.0011914958305639057 54.91 51.37 63.75 60.16 78.63 61.05 64.81 54.53 74.05 53.21 71.06 53.26 78.57 63.24 55.76 50.16 63.81 50.79 54.88 48.32 56.47 48.58 53.41 58.79 65.01 56.79 77.39 58.21 77.03 54.42 52.78 50.05
Wang_USTC_task2_1 WangUSTC2024 19 59.683659221054455 ± 0.0011407300964302418 54.82 51.37 63.64 60.16 61.90 50.24 64.81 54.53 74.06 53.21 71.07 53.26 71.53 51.21 55.88 50.16 63.80 50.79 60.14 49.91 70.44 55.14 70.78 59.75 59.67 57.30 67.09 52.13 72.33 54.91 80.04 67.37
Lee_KNU_task2_3 LeeKNU2024 73 50.31619240957195 ± 0.0009955894014041765 54.53 49.68 54.53 48.11 63.57 50.95 40.12 49.74 43.15 49.00 43.09 51.05 64.12 49.32 53.45 55.16 47.89 50.63 45.40 49.26 69.42 53.75 66.54 56.16 59.48 52.16 63.74 51.63 63.06 51.21 45.16 48.26
Qian_NIVIC_task2_1 QianNIVIC2024 14 60.49793602398476 ± 0.0011415310840067227 54.91 51.37 63.64 60.16 73.40 53.00 64.80 54.53 74.16 53.21 71.08 53.26 71.53 51.21 55.78 50.16 63.70 50.79 59.21 49.42 68.92 54.84 69.78 58.47 58.80 56.37 68.15 52.84 71.22 54.89 78.94 66.74
Jiang_CUP_task2_2 JiangCUP2024 80 49.54166350875297 ± 0.0009707659088424591 55.62 53.32 49.99 48.68 51.88 49.53 54.41 49.32 42.47 48.21 50.59 51.00 51.49 48.32 46.74 49.37 45.96 47.89 47.96 48.63 46.36 51.26 62.98 53.73 62.88 55.73 70.42 54.15 90.34 69.52 82.16 67.10
Jiang_THUEE_task2_1 JiangTHUEE2024 4 65.36869889765188 ± 0.001185491785330456 64.77 53.53 68.31 53.37 67.82 53.79 69.81 54.63 73.21 57.74 72.70 57.16 93.07 76.89 67.46 54.89 67.72 52.95 62.68 51.05 71.04 58.53 71.66 57.21 63.46 58.26 76.87 61.79 89.51 65.68 81.54 68.00
Lv_AITHU_task2_4 LvAITHU2024 1 66.24102452310362 ± 0.0011854991900309608 68.07 56.11 64.88 50.84 69.26 54.05 73.14 54.79 74.73 56.84 72.89 54.58 94.89 79.26 72.35 59.74 67.69 52.11 63.45 48.63 70.37 57.68 73.39 62.11 65.41 60.05 76.93 62.63 88.50 61.53 81.93 64.68
Yin_Midea_task2_2 YinMidea2024 63 52.23563242136593 ± 0.0010200734060762124 62.26 50.68 53.81 48.32 51.02 51.21 61.81 51.95 46.85 54.42 67.66 60.21 51.86 48.79 45.61 48.79 42.77 51.47 50.78 50.53 66.56 58.16 70.36 54.42 63.22 56.16 75.26 53.63 91.94 73.68 76.76 63.84
Perez_UPV_task2_1 PerezUPV2024 85 48.98393318219933 ± 0.0009685037559411823 53.60 51.13 47.61 49.16 50.71 49.74 40.66 48.23 41.77 49.83 49.17 49.66 49.54 50.01 44.25 51.63 65.35 54.98 56.24 56.06 69.02 66.19 60.71 59.84 59.00
Wu_IACAS_task2_3 WuIACAS2024 47 54.16899844515759 ± 0.001057108336360687 61.69 53.47 55.90 48.47 52.08 51.21 53.71 48.63 52.53 51.95 66.58 55.00 66.90 49.68 43.65 50.89 60.10 47.89 49.46 48.63 64.08 53.84 69.84 59.47 62.61 55.42 77.56 60.00 93.80 73.21 75.92 64.36
Li_SMALLRICE_task2_3 LiSMALLRICE2024 53 53.81856456562342 ± 0.0011243926792786517 51.46 50.00 49.04 48.37 54.65 53.74 55.68 49.11 45.79 53.63 65.34 50.16 93.89 74.63 40.74 51.16 56.53 54.68 55.64 49.21 66.26 53.53 66.68 55.42 65.74 57.84 77.52 59.16 69.82 51.47 77.02 65.21
Huang_Xju_task2_1 HuangXju2024 46 54.38612240957236 ± 0.001005392973156531 54.05 49.84 58.72 58.63 67.92 52.21 53.68 48.53 57.09 55.00 45.11 50.16 54.60 49.79 62.31 52.89 55.06 49.32 49.89 50.57 49.98 47.68 54.82 59.31 61.59 52.26 73.29 51.94 70.10 48.21 52.55 51.68
Guo_BIT_task2_3 GuoBIT2024 48 54.084345600639494 ± 0.0010037944335590143 65.66 51.26 59.86 53.84 57.17 50.47 59.52 55.32 52.75 56.79 52.10 52.32 54.94 48.42 53.79 50.16 46.16 49.32 48.16 51.58 59.22 49.16 55.92 59.11 55.92 50.84 81.31 57.79 78.01 58.32 49.28 51.11
Wan_HFUU_task2_1 WanHFUU2024 37 56.95741891894512 ± 0.0010154269725155024 62.30 51.63 63.32 51.53 55.72 53.58 55.58 51.26 50.91 55.16 60.41 55.63 64.45 51.89 61.04 53.84 65.54 47.89 51.10 49.20 70.44 52.57 64.40 57.57 62.80 55.42 75.68 54.31 91.74 70.84 76.82 63.21
Kong_IMECAS_task2_2 KongIMECAS2024 40 56.50382577391263 ± 0.0009983711243153732 55.91 51.16 64.26 60.68 77.64 60.16 59.36 52.05 53.65 53.95 51.42 51.05 52.16 48.47 65.65 53.84 54.09 49.16 49.86 51.21 50.65 47.89 54.30 58.95 60.62 52.05 77.56 54.79 77.83 48.84 52.46 50.74
Hai_SCU_task2_1 HaiSCU2024 72 50.34153796416583 ± 0.0010155482504932121 57.31 51.00 41.57 47.84 65.33 57.16 54.01 54.53 41.13 47.84 57.91 55.74 49.20 48.58 46.77 49.53 46.16 50.53 49.64 51.21 54.78 48.78 66.57 60.36 51.51 48.95 62.52 50.47 63.18 48.89 51.29 50.94
Kim_DAU_task2_1 KimDAU2024 71 50.433236408626016 ± 0.0010116627475769257 69.05 52.05 46.70 48.32 50.78 49.68 49.59 49.63 57.53 54.21 51.58 50.11 45.57 49.05 46.63 49.42 45.13 50.00 66.83 66.65 62.39 53.43 80.15 70.95 75.95 75.95 73.51 72.32 79.72 71.36 78.03 72.48
Bian_NR_task2_2 BianNR2024 74 50.30296617352682 ± 0.0009936159397799474 59.33 62.84 52.88 49.74 58.74 51.74 43.64 48.89 51.73 51.68 51.21 50.53 52.51 49.00 38.20 49.95 47.03 51.84 42.45 51.05 61.04 52.63 61.91 56.95 54.52 50.00 54.82 51.63 49.69 50.58 48.06 49.26
Gleichmann_TNT_task2_1 GleichmannTNT2024 93 45.314372753290186 ± 0.0009577819435369494 49.30 49.37 49.06 49.26 48.12 48.63 33.24 48.32 29.82 50.42 48.21 53.37 48.73 50.37 40.46 50.95 55.87 55.37 57.34 50.05 59.56 52.68 62.16 52.32 54.56 51.74 59.38 53.16 73.42 57.74 58.48 49.95
Kim_CAU_task2_1 KimCAU2024 89 46.45632996840251 ± 0.0010088781424119019 45.63 50.37 42.38 47.89 42.28 49.16 38.85 51.58 41.32 51.95 56.60 50.53 50.01 50.42 44.30 49.79 46.82 49.11 47.70 49.11 56.48 51.58 60.34 53.26 58.14 57.37 62.30 52.42 77.70 49.53 65.50 56.79
Zhang_HEU_task2_1 ZhangHEU2024 54 53.74623090811457 ± 0.001070067273571812 64.76 53.95 56.05 51.32 49.93 49.79 61.59 56.63 50.50 54.42 47.10 50.42 59.50 48.00 58.03 51.79 50.86 50.79 45.17 49.37 61.37 50.05 56.23 58.00 58.81 51.74 81.43 61.05 85.73 78.84 73.25 56.63
Liu_CXL_task2_1 LiuCXL2024 13 60.52026046959108 ± 0.0011605372202239733 54.82 51.37 63.76 60.16 61.91 50.24 64.81 54.53 74.04 53.21 71.15 53.26 78.56 63.24 55.87 50.16 63.70 50.79 58.38 49.43 68.99 54.26 69.94 57.44 57.45 55.74 67.03 52.54 70.32 55.24 79.75 65.69
Guan_HEU_task2_4 GuanHEU2024 43 55.56904711277052 ± 0.0010596716564482372 60.80 51.05 61.57 50.42 62.33 53.42 58.52 49.32 60.31 55.63 58.50 56.11 59.44 51.95 54.08 53.32 46.05 48.53 52.52 49.58 70.52 52.32 63.66 53.84 60.77 55.79 70.29 51.42 89.24 76.00 81.29 65.63
Wang_iflytek_task2_1 Wangiflytek2024 11 61.08842633062041 ± 0.0011747355735174372 54.87 51.37 63.72 60.16 78.59 61.05 64.76 54.53 74.08 53.21 71.11 53.26 71.52 51.21 55.83 50.16 63.75 50.79 60.37 51.13 69.31 55.32 71.55 58.90 60.14 57.35 68.38 53.86 72.44 55.67 80.31 67.34
Yang_IND_task2_1 YangIND2024 10 61.35410342629337 ± 0.001148839259798822 54.91 51.37 63.77 60.16 73.30 53.00 64.81 54.53 74.03 53.21 71.16 53.26 78.56 63.24 55.78 50.16 63.70 50.79 55.63 47.28 55.48 47.79 52.98 57.09 64.15 54.98 76.33 60.04 75.31 55.65 53.61 49.98


Supplementary metrics (recall, precision, and F1 score)

Rank Submission Information Evaluation Dataset
Submission Code Technical
Report
Official
Rank
3DPrinter
(F1 score)
3DPrinter
(Recall)
3DPrinter
(Precision)
AirCompressor
(F1 score)
AirCompressor
(Recall)
AirCompressor
(Precision)
BrushlessMotor
(F1 score)
BrushlessMotor
(Recall)
BrushlessMotor
(Precision)
HairDryer
(F1 score)
HairDryer
(Recall)
HairDryer
(Precision)
HoveringDrone
(F1 score)
HoveringDrone
(Recall)
HoveringDrone
(Precision)
RoboticArm
(F1 score)
RoboticArm
(Recall)
RoboticArm
(Precision)
Scanner
(F1 score)
Scanner
(Recall)
Scanner
(Precision)
ToothBrush
(F1 score)
ToothBrush
(Recall)
ToothBrush
(Precision)
ToyCircuit
(F1 score)
ToyCircuit
(Recall)
ToyCircuit
(Precision)
DCASE2024_baseline_task2_MSE DCASE2024baseline2024 39 66.64 74.68 60.17 53.49 54.11 52.88 66.67 100.00 50.00 62.65 82.02 50.68 61.92 64.86 59.23 66.43 97.96 50.25 65.89 75.34 58.55 66.67 100.00 50.00 70.50 95.83 55.76
Wilkinghoff_FKIE_task2_1 WilkinghoffFKIE2024 62 64.52 71.11 59.04 15.86 10.18 35.90 61.35 80.40 49.60 65.16 83.72 53.33 36.36 27.59 53.33 70.19 97.96 54.68 11.15 7.11 25.81 58.14 66.67 51.55 18.22 11.22 48.50
Fujimura_NU_task2_1 FujimuraNU2024 26 64.46 58.17 72.28 11.76 6.86 41.38 59.68 68.64 52.80 40.92 29.76 65.46 23.92 14.40 70.59 67.34 100.00 50.76 6.26 3.60 24.00 67.03 69.92 64.38 7.29 3.90 55.71
Zhao_CUMT_task2_1 ZhaoCUMT2024 9 52.89 52.81 52.97 55.65 54.86 56.47 70.06 69.94 70.18 56.28 56.14 56.42 70.00 70.00 70.00 66.00 66.00 66.00 78.59 78.38 78.80 53.90 53.70 54.10 63.62 63.44 63.80
Wang_USTC_task2_1 WangUSTC2024 19 52.14 52.08 52.21 54.51 53.53 55.53 57.53 56.14 59.00 56.28 56.14 56.42 70.00 70.00 70.00 66.00 66.00 66.00 62.86 60.55 65.34 54.96 54.84 55.08 63.62 63.44 63.80
Lee_KNU_task2_3 LeeKNU2024 73 53.93 53.33 54.55 58.00 58.00 58.00 60.00 60.00 60.00 18.09 11.27 45.92 0.00 0.00 0.00 46.14 43.10 49.65 57.46 54.19 61.14 48.23 37.89 66.30 22.40 14.79 46.12
Qian_NIVIC_task2_1 QianNIVIC2024 14 53.33 53.33 53.33 54.51 53.53 55.53 67.14 67.06 67.22 55.84 55.58 56.11 70.97 70.99 70.95 66.00 66.00 66.00 63.44 61.54 65.47 53.86 53.70 54.02 62.70 62.60 62.80
Jiang_CUP_task2_2 JiangCUP2024 80 32.75 21.91 64.78 10.24 6.22 28.87 46.07 40.98 52.60 40.00 32.00 53.33 26.32 18.11 48.10 61.25 74.99 51.77 10.26 6.22 29.17 23.24 14.81 53.91 17.84 10.71 53.19
Jiang_THUEE_task2_1 JiangTHUEE2024 4 56.33 55.52 57.17 60.79 60.59 60.99 63.02 62.98 63.06 61.98 61.71 62.25 68.44 68.64 68.24 64.37 64.62 64.12 86.06 85.58 86.55 61.18 60.39 61.99 62.86 62.86 62.86
Lv_AITHU_task2_4 LvAITHU2024 1 58.46 57.31 59.66 59.97 59.93 60.01 64.86 64.86 64.86 66.41 66.27 66.55 65.88 65.88 65.88 67.17 67.47 66.88 90.02 89.60 90.44 62.44 60.94 64.02 63.98 63.94 64.02
Yin_Midea_task2_2 YinMidea2024 63 57.25 50.04 66.88 12.97 8.00 34.29 43.64 38.40 50.53 36.89 27.69 55.21 32.94 24.56 50.00 67.34 100.00 50.76 11.15 7.06 26.55 44.21 37.33 54.19 13.18 7.56 51.52
Perez_UPV_task2_1 PerezUPV2024 85 67.59 98.00 51.58 66.67 100.00 50.00 66.67 100.00 50.00 63.32 89.29 49.05 66.67 100.00 50.00 42.75 39.07 47.19 16.11 9.60 50.00 66.67 100.00 50.00 65.45 70.87 60.80
Wu_IACAS_task2_3 WuIACAS2024 47 60.12 57.38 63.13 15.38 9.60 38.71 66.60 87.64 53.71 55.84 58.22 53.64 32.94 24.56 50.00 66.69 93.83 51.72 16.09 10.00 41.10 53.69 50.75 56.99 65.48 75.79 57.65
Li_SMALLRICE_task2_3 LiSMALLRICE2024 53 63.38 74.72 55.02 14.10 8.73 36.64 56.93 57.75 56.14 25.42 16.97 50.63 30.77 21.43 54.55 69.46 84.05 59.19 84.07 96.91 74.24 63.69 66.67 60.98 35.29 24.08 66.01
Huang_Xju_task2_1 HuangXju2024 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 66.67 100.00 50.00
Guo_BIT_task2_3 GuoBIT2024 48 64.22 64.62 63.83 56.08 55.36 56.82 54.72 53.43 56.07 51.62 47.36 56.72 7.28 3.92 50.51 50.00 50.00 50.00 50.71 48.44 53.22 56.52 52.88 60.70 51.72 46.98 57.52
Wan_HFUU_task2_1 WanHFUU2024 37 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 66.67 100.00 50.00
Kong_IMECAS_task2_2 KongIMECAS2024 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 66.67 100.00 50.00
Hai_SCU_task2_1 HaiSCU2024 72 58.01 57.93 58.09 41.13 40.19 42.13 61.03 60.85 61.21 49.52 49.28 49.76 38.54 29.89 54.25 56.00 56.00 56.00 49.06 47.69 50.52 48.51 47.35 49.72 46.33 39.25 56.52
Kim_DAU_task2_1 KimDAU2024 71 65.60 60.98 70.97 26.37 19.09 42.60 56.29 58.41 54.31 40.39 36.71 44.89 53.33 48.48 59.26 57.14 64.86 51.06 16.75 10.67 39.02 47.06 48.48 45.71 48.92 50.75 47.22
Bian_NR_task2_2 BianNR2024 74 46.09 32.94 76.71 16.65 9.43 70.97 25.51 16.42 57.14 16.05 9.60 48.98 21.05 13.33 50.00 41.90 34.32 53.79 40.17 31.54 55.31 50.00 48.48 51.61 58.03 62.61 54.08
Gleichmann_TNT_task2_1 GleichmannTNT2024 93 55.53 65.76 48.06 52.53 54.86 50.39 39.72 30.91 55.56 0.00 0.00 0.00 0.00 0.00 0.00 38.30 36.00 40.91 20.40 13.22 44.71 66.67 100.00 50.00 0.00 0.00 0.00
Kim_CAU_task2_1 KimCAU2024 89 31.19 23.04 48.24 9.88 6.00 27.91 6.59 3.50 56.00 0.00 0.00 0.00 33.23 26.98 43.24 0.00 0.00 0.00 29.82 22.61 43.77 48.89 45.04 53.47 0.00 0.00 0.00
Zhang_HEU_task2_1 ZhangHEU2024 54 57.70 52.08 64.70 51.67 45.96 59.02 36.56 28.96 49.59 46.50 36.71 63.41 0.00 0.00 0.00 35.85 29.47 45.75 20.95 14.44 38.12 56.33 50.08 64.36 28.99 19.64 55.38
Liu_CXL_task2_1 LiuCXL2024 13 52.14 52.08 52.21 55.65 54.86 56.47 57.53 56.14 59.00 55.84 55.58 56.11 70.00 70.00 70.00 66.98 66.99 66.97 78.59 78.38 78.80 54.79 54.55 55.05 62.75 62.60 62.90
Guan_HEU_task2_4 GuanHEU2024 43 59.94 63.44 56.82 58.99 57.38 60.69 55.65 54.86 56.47 50.79 47.72 54.29 54.56 49.35 61.00 50.43 47.08 54.30 48.94 43.52 55.91 43.68 34.69 58.95 34.04 24.37 56.43
Wang_iflytek_task2_1 Wangiflytek2024 11 52.14 52.08 52.21 55.65 54.86 56.47 69.08 68.87 69.29 55.01 54.86 55.17 70.00 70.00 70.00 66.00 66.00 66.00 62.86 60.55 65.34 54.96 54.84 55.08 62.75 62.60 62.90
Yang_IND_task2_1 YangIND2024 10 52.89 52.81 52.97 55.65 54.86 56.47 65.97 65.79 66.15 55.84 55.58 56.11 70.00 70.00 70.00 67.01 66.99 67.03 78.59 78.38 78.80 53.86 53.70 54.02 62.70 62.60 62.80



Systems ranking

Rank Submission Information Evaluation Dataset Development Dataset
Submission Code Technical
Report
Official
Rank
Official
Score
3DPrinter
(AUC)
3DPrinter
(pAUC)
AirCompressor
(AUC)
AirCompressor
(pAUC)
BrushlessMotor
(AUC)
BrushlessMotor
(pAUC)
HairDryer
(AUC)
HairDryer
(pAUC)
HoveringDrone
(AUC)
HoveringDrone
(pAUC)
RoboticArm
(AUC)
RoboticArm
(pAUC)
Scanner
(AUC)
Scanner
(pAUC)
ToothBrush
(AUC)
ToothBrush
(pAUC)
ToyCircuit
(AUC)
ToyCircuit
(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)
DCASE2024_baseline_task2_MAHALA DCASE2024baseline2024 41 56.489334216102336 ± 0.001002115182882003 54.29 50.84 60.34 60.79 76.69 59.05 59.78 55.11 59.75 58.00 49.18 51.79 56.16 49.26 61.49 48.37 53.88 49.21 50.18 51.04 50.99 48.21 53.00 58.82 61.04 53.44 78.08 55.74 71.73 49.05 54.65 51.26
DCASE2024_baseline_task2_MSE DCASE2024baseline2024 39 56.50830191796572 ± 0.001050516938082758 59.72 49.42 55.38 55.47 66.92 55.58 52.89 51.63 58.11 50.21 50.96 51.16 60.48 50.11 72.15 52.74 62.41 50.00 50.37 48.77 61.77 47.95 61.70 57.58 61.47 57.53 69.87 55.65 61.26 51.77 48.66 52.42
Wilkinghoff_FKIE_task2_1 WilkinghoffFKIE2024 62 52.46265926819839 ± 0.0010707667655151189 67.11 58.74 53.56 48.63 47.76 50.68 57.02 56.32 43.14 53.26 67.81 58.11 58.67 49.16 41.68 52.00 48.59 48.00 50.45 49.40 60.65 53.50 68.60 58.80 75.10 59.50 72.55 54.80 86.25 65.60 77.30 68.30
Wilkinghoff_FKIE_task2_2 WilkinghoffFKIE2024 67 51.45784872819026 ± 0.0010613673898969037 65.63 54.42 50.61 48.84 48.03 50.84 58.13 56.11 41.64 49.63 63.31 54.32 49.73 49.05 46.30 55.95 48.02 48.05 57.70 50.00 64.00 54.10 74.50 60.30 67.25 54.90 74.85 58.10 87.65 68.50 75.75 69.30
Wilkinghoff_FKIE_task2_3 WilkinghoffFKIE2024 69 51.23779473216818 ± 0.0010540273988512347 65.59 58.47 49.04 48.79 50.68 51.95 59.74 57.42 39.52 48.95 59.74 53.63 52.00 48.63 44.80 54.37 47.01 48.32 56.95 51.10 63.30 55.40 73.55 60.50 67.15 53.30 72.05 57.30 86.95 65.80 75.15 67.70
Fujimura_NU_task2_1 FujimuraNU2024 26 58.89866752033418 ± 0.001041273079131894 73.17 59.79 60.48 49.05 56.59 50.53 65.50 52.68 66.39 53.16 70.58 57.68 60.86 50.37 71.18 56.11 47.10 48.68 54.41 49.84 75.94 59.74 75.75 61.16 63.17 56.68 72.28 54.53 93.24 80.37 78.61 69.16
Fujimura_NU_task2_2 FujimuraNU2024 35 57.532141353597495 ± 0.0010455433495501576 73.45 60.32 63.14 49.53 53.02 50.21 65.09 51.84 60.06 54.05 70.73 58.16 61.57 50.16 56.32 54.11 48.02 48.47 55.98 50.58 69.11 52.84 75.62 61.32 64.36 56.95 71.69 53.26 89.40 66.16 77.34 66.84
Fujimura_NU_task2_3 FujimuraNU2024 28 58.53027365695134 ± 0.0010570956736933555 73.10 59.11 58.86 49.05 56.51 50.79 66.16 54.05 63.81 51.21 67.75 55.53 60.31 50.32 73.93 56.68 47.23 49.11 53.65 49.84 69.59 60.16 75.44 61.47 63.96 56.79 71.33 53.74 94.55 84.95 77.73 70.42
Fujimura_NU_task2_4 FujimuraNU2024 27 58.873674197238635 ± 0.0010315496724687262 72.85 59.21 58.43 49.05 55.39 51.00 64.20 51.89 70.97 54.79 71.51 58.95 60.48 50.11 72.63 55.84 46.34 48.74 54.30 49.00 75.36 60.37 75.47 60.47 60.56 55.79 73.21 56.26 93.67 83.68 78.53 70.00
Zhao_CUMT_task2_1 ZhaoCUMT2024 9 61.96515488201288 ± 0.0011914958305639057 54.91 51.37 63.75 60.16 78.63 61.05 64.81 54.53 74.05 53.21 71.06 53.26 78.57 63.24 55.76 50.16 63.81 50.79 54.88 48.32 56.47 48.58 53.41 58.79 65.01 56.79 77.39 58.21 77.03 54.42 52.78 50.05
Zhao_CUMT_task2_2 ZhaoCUMT2024 12 60.55214715135816 ± 0.0011622221324711875 54.91 51.37 52.46 49.89 78.63 61.05 64.81 54.53 74.05 53.21 71.06 53.26 78.57 63.24 55.76 50.16 63.81 50.79 54.97 49.55 55.61 48.65 53.41 58.79 64.38 56.12 76.10 57.21 75.93 54.23 52.37 49.11
Zhao_CUMT_task2_3 ZhaoCUMT2024 15 60.39913436930961 ± 0.001192077122815144 54.91 51.37 63.75 60.16 78.63 61.05 64.81 54.53 74.05 53.21 53.34 48.26 78.57 63.24 55.76 50.16 63.81 50.79 54.94 47.45 53.81 48.35 57.98 57.79 62.85 51.94 75.11 53.96 74.54 49.36 51.70 49.33
Zhao_CUMT_task2_4 ZhaoCUMT2024 23 59.05587078043073 ± 0.0011118351899573856 54.91 51.37 52.46 49.89 78.63 61.05 64.81 54.53 74.05 53.21 53.34 48.26 78.57 63.24 55.76 50.16 63.81 50.79 56.02 48.58 55.09 49.37 58.94 58.74 63.41 52.95 75.29 54.79 75.19 49.74 51.64 49.68
Wang_USTC_task2_1 WangUSTC2024 19 59.683659221054455 ± 0.0011407300964302418 54.82 51.37 63.64 60.16 61.90 50.24 64.81 54.53 74.06 53.21 71.07 53.26 71.53 51.21 55.88 50.16 63.80 50.79 60.14 49.91 70.44 55.14 70.78 59.75 59.67 57.30 67.09 52.13 72.33 54.91 80.04 67.37
Wang_USTC_task2_2 WangUSTC2024 30 58.37825228494783 ± 0.0011047130855523176 54.82 51.37 52.46 49.89 61.90 50.24 64.81 54.53 74.06 53.21 71.07 53.26 71.53 51.21 55.88 50.16 63.80 50.79 60.14 49.91 70.44 55.14 70.78 59.75 59.67 57.30 67.09 52.13 72.33 54.91 80.04 67.37
Wang_USTC_task2_3 WangUSTC2024 32 58.22887759850294 ± 0.0010416091654744295 54.82 51.37 63.64 60.16 61.90 50.24 64.81 54.53 74.06 53.21 53.33 48.26 71.53 51.21 55.88 50.16 63.80 50.79 60.14 49.91 70.44 55.14 70.78 59.75 59.67 57.30 67.09 52.13 72.33 54.91 80.04 67.37
Wang_USTC_task2_4 WangUSTC2024 36 56.98567054157987 ± 0.000993057635763809 54.82 51.37 52.46 49.89 61.90 50.24 64.81 54.53 74.06 53.21 53.33 48.26 71.53 51.21 55.88 50.16 63.80 50.79 60.14 49.91 70.44 55.14 70.78 59.75 59.67 57.30 67.09 52.13 72.33 54.91 80.04 67.37
Lee_KNU_task2_1 LeeKNU2024 75 50.24397240705927 ± 0.0010165017564282086 58.85 52.53 55.61 48.74 57.55 51.11 40.75 49.68 44.32 48.42 43.85 50.79 57.30 48.89 54.27 57.21 45.28 51.53 45.64 48.21 71.00 52.32 65.90 56.74 55.72 53.63 61.18 55.47 61.60 52.53 47.04 48.26
Lee_KNU_task2_2 LeeKNU2024 79 49.690264893541816 ± 0.0009967144688343946 55.07 49.68 53.99 48.21 59.23 50.79 37.54 49.21 43.27 48.79 43.86 51.26 62.43 49.53 51.61 54.79 47.92 51.84 42.94 49.42 60.52 52.47 67.04 57.21 62.58 57.00 58.32 54.16 63.72 52.16 44.56 48.53
Lee_KNU_task2_3 LeeKNU2024 73 50.31619240957195 ± 0.0009955894014041765 54.53 49.68 54.53 48.11 63.57 50.95 40.12 49.74 43.15 49.00 43.09 51.05 64.12 49.32 53.45 55.16 47.89 50.63 45.40 49.26 69.42 53.75 66.54 56.16 59.48 52.16 63.74 51.63 63.06 51.21 45.16 48.26
Lee_KNU_task2_4 LeeKNU2024 77 49.75884067621996 ± 0.0010006630722986074 54.68 49.47 54.00 48.37 60.08 50.84 36.81 49.21 43.71 49.11 43.48 51.26 61.99 49.47 52.68 55.63 48.62 51.74 42.76 49.68 68.02 51.89 66.48 56.47 61.50 56.32 63.88 51.89 64.40 52.95 44.60 48.63
Qian_NIVIC_task2_1 QianNIVIC2024 14 60.49793602398476 ± 0.0011415310840067227 54.91 51.37 63.64 60.16 73.40 53.00 64.80 54.53 74.16 53.21 71.08 53.26 71.53 51.21 55.78 50.16 63.70 50.79 59.21 49.42 68.92 54.84 69.78 58.47 58.80 56.37 68.15 52.84 71.22 54.89 78.94 66.74
Qian_NIVIC_task2_2 QianNIVIC2024 22 59.14659735390466 ± 0.0010937560006732772 54.91 51.37 52.35 49.89 73.40 53.00 64.80 54.53 74.16 53.21 71.08 53.26 71.53 51.21 55.78 50.16 63.70 50.79 59.21 49.42 68.92 54.84 69.78 58.47 58.80 56.37 68.15 52.84 71.22 54.89 78.94 66.74
Qian_NIVIC_task2_3 QianNIVIC2024 25 59.00312635614466 ± 0.0011170532039945762 54.91 51.37 63.64 60.16 73.40 53.00 64.80 54.53 74.16 53.21 53.33 48.26 71.53 51.21 55.78 50.16 63.70 50.79 59.21 49.42 68.92 54.84 69.78 58.47 58.80 56.37 68.15 52.84 71.22 54.89 78.94 66.74
Qian_NIVIC_task2_4 QianNIVIC2024 34 57.71703181759845 ± 0.0010255811693124191 54.91 51.37 52.35 49.89 73.40 53.00 64.80 54.53 74.16 53.21 53.33 48.26 71.53 51.21 55.78 50.16 63.70 50.79 59.21 49.42 68.92 54.84 69.78 58.47 58.80 56.37 68.15 52.84 71.22 54.89 78.94 66.74
Jiang_CUP_task2_1 JiangCUP2024 81 49.48958984650561 ± 0.0009901396645261601 64.32 51.84 51.05 48.11 53.21 51.00 52.66 49.84 39.94 48.32 57.92 51.53 53.75 48.32 40.17 50.05 42.69 48.21 48.23 49.36 60.84 53.10 61.19 55.94 61.96 57.68 68.56 50.84 89.24 64.52 81.50 65.73
Jiang_CUP_task2_2 JiangCUP2024 80 49.54166350875297 ± 0.0009707659088424591 55.62 53.32 49.99 48.68 51.88 49.53 54.41 49.32 42.47 48.21 50.59 51.00 51.49 48.32 46.74 49.37 45.96 47.89 47.96 48.63 46.36 51.26 62.98 53.73 62.88 55.73 70.42 54.15 90.34 69.52 82.16 67.10
Jiang_CUP_task2_3 JiangCUP2024 84 48.99951485756926 ± 0.0009749502685763356 59.19 49.21 51.44 48.42 51.44 50.79 49.26 49.95 40.94 47.37 55.97 51.32 49.11 48.16 48.50 51.53 39.86 48.32 48.56 49.31 56.09 51.47 62.92 55.10 62.66 59.89 69.62 50.79 93.38 71.57 83.64 69.57
Jiang_CUP_task2_4 JiangCUP2024 82 49.22249405887789 ± 0.000994320172050672 59.69 51.05 51.16 48.89 49.26 48.79 48.87 49.00 41.40 50.84 57.52 51.63 49.98 48.47 48.15 51.42 40.97 47.84 45.42 48.57 57.00 52.36 60.16 53.79 60.78 58.79 70.24 52.42 87.52 64.42 86.94 69.68
Jiang_THUEE_task2_1 JiangTHUEE2024 4 65.36869889765188 ± 0.001185491785330456 64.77 53.53 68.31 53.37 67.82 53.79 69.81 54.63 73.21 57.74 72.70 57.16 93.07 76.89 67.46 54.89 67.72 52.95 62.68 51.05 71.04 58.53 71.66 57.21 63.46 58.26 76.87 61.79 89.51 65.68 81.54 68.00
Jiang_THUEE_task2_2 JiangTHUEE2024 6 64.54151796485333 ± 0.0011315770633509113 64.24 53.63 64.77 52.89 67.09 54.63 72.46 54.16 73.28 59.63 62.59 53.63 93.07 76.89 68.28 56.16 68.31 52.47 63.64 49.58 70.50 56.58 73.46 59.05 65.01 57.84 85.80 65.89 89.11 68.58 80.05 61.74
Jiang_THUEE_task2_3 JiangTHUEE2024 7 64.1653429214525 ± 0.0011555541315495161 64.24 53.32 67.29 53.16 64.63 53.68 70.54 54.21 73.79 57.68 71.33 54.68 88.49 58.26 69.52 55.53 67.95 51.95 61.77 49.00 70.76 57.32 73.01 59.68 63.83 57.74 76.95 62.32 88.98 63.79 84.82 66.74
Jiang_THUEE_task2_4 JiangTHUEE2024 8 63.96711447500272 ± 0.001131928850363913 64.24 53.32 67.29 53.16 64.63 53.68 70.54 54.21 73.79 57.68 68.16 54.68 88.49 58.26 69.52 55.53 67.95 51.95 61.77 49.00 70.76 57.32 73.01 59.68 63.83 57.74 83.42 66.47 89.45 68.89 81.32 66.74
Lv_AITHU_task2_1 LvAITHU2024 3 65.9743472963728 ± 0.0011594559701770019 66.59 55.74 66.03 54.21 71.21 56.11 72.51 54.95 74.27 57.95 71.05 54.68 93.21 76.26 67.51 55.79 68.18 53.26 63.72 52.26 69.52 56.84 73.05 57.95 64.37 58.37 75.65 61.79 86.62 61.95 79.74 66.58
Lv_AITHU_task2_2 LvAITHU2024 5 64.95825202580062 ± 0.00112965431185421 64.24 53.63 64.77 52.89 67.09 54.63 72.46 54.16 73.28 59.63 68.29 53.68 93.07 76.89 68.28 56.16 68.31 52.47 63.64 49.58 70.50 56.58 73.46 59.05 65.01 57.84 73.85 58.89 85.25 59.21 80.05 61.74
Lv_AITHU_task2_3 LvAITHU2024 2 66.16902475266467 ± 0.0011908734444371603 67.55 57.32 65.17 50.63 73.58 54.05 72.70 56.21 73.98 56.58 72.30 55.53 94.88 82.26 68.97 57.42 66.06 51.89 63.88 50.68 69.57 56.74 72.17 59.68 65.33 61.16 76.21 60.37 89.53 64.42 82.21 68.68
Lv_AITHU_task2_4 LvAITHU2024 1 66.24102452310362 ± 0.0011854991900309608 68.07 56.11 64.88 50.84 69.26 54.05 73.14 54.79 74.73 56.84 72.89 54.58 94.89 79.26 72.35 59.74 67.69 52.11 63.45 48.63 70.37 57.68 73.39 62.11 65.41 60.05 76.93 62.63 88.50 61.53 81.93 64.68
Yin_Midea_task2_1 YinMidea2024 68 51.3642460731876 ± 0.0010446326970144333 52.20 51.95 62.19 50.47 49.29 50.32 57.69 51.58 44.57 51.79 62.74 51.74 52.63 48.74 43.78 50.79 46.56 51.58 56.82 48.68 61.16 50.26 70.54 59.89 65.46 55.00 71.28 52.26 76.10 70.79 78.34 65.00
Yin_Midea_task2_2 YinMidea2024 63 52.23563242136593 ± 0.0010200734060762124 62.26 50.68 53.81 48.32 51.02 51.21 61.81 51.95 46.85 54.42 67.66 60.21 51.86 48.79 45.61 48.79 42.77 51.47 50.78 50.53 66.56 58.16 70.36 54.42 63.22 56.16 75.26 53.63 91.94 73.68 76.76 63.84
Yin_Midea_task2_3 YinMidea2024 83 49.080583650031464 ± 0.0010066512326207871 58.08 51.00 52.02 48.58 49.40 53.47 49.44 49.89 44.17 53.16 56.78 52.05 47.57 48.68 44.39 51.79 38.87 48.95 52.24 49.53 66.82 60.58 64.74 55.89 59.68 55.89 68.06 55.26 92.36 72.37 80.18 69.63
Yin_Midea_task2_4 YinMidea2024 70 50.60604025688289 ± 0.0010345626785820143 53.73 50.63 53.38 48.79 44.34 52.58 59.50 52.95 45.86 53.58 65.75 56.74 59.01 49.32 39.49 50.00 43.25 48.58 47.82 48.00 67.12 53.74 64.80 51.79 62.64 57.11 68.80 51.68 92.16 75.26 76.48 64.16
Perez_UPV_task2_1 PerezUPV2024 85 48.98393318219933 ± 0.0009685037559411823 53.60 51.13 47.61 49.16 50.71 49.74 40.66 48.23 41.77 49.83 49.17 49.66 49.54 50.01 44.25 51.63 65.35 54.98 56.24 56.06 69.02 66.19 60.71 59.84 59.00
Wu_IACAS_task2_1 WuIACAS2024 61 52.50061129302863 ± 0.0010378134153598755 61.93 54.37 56.24 48.37 45.93 50.37 52.89 49.37 52.94 52.00 64.35 52.63 50.06 49.05 43.85 50.32 62.33 47.89 49.62 49.21 60.82 53.26 68.76 59.78 64.08 55.52 72.70 57.68 95.72 80.47 75.36 64.21
Wu_IACAS_task2_2 WuIACAS2024 50 54.02394583622731 ± 0.001088203562160475 61.28 52.32 55.38 48.47 51.50 51.79 52.04 49.16 51.45 50.79 65.40 54.32 71.54 50.95 43.56 51.95 59.96 48.26 49.84 48.31 64.44 53.15 70.64 59.89 62.52 56.21 77.92 60.05 93.03 66.15 75.74 64.36
Wu_IACAS_task2_3 WuIACAS2024 47 54.16899844515759 ± 0.001057108336360687 61.69 53.47 55.90 48.47 52.08 51.21 53.71 48.63 52.53 51.95 66.58 55.00 66.90 49.68 43.65 50.89 60.10 47.89 49.46 48.63 64.08 53.84 69.84 59.47 62.61 55.42 77.56 60.00 93.80 73.21 75.92 64.36
Wu_IACAS_task2_4 WuIACAS2024 66 51.777140739159734 ± 0.0010371057163386184 61.55 54.68 53.63 49.32 52.99 52.16 47.96 49.53 47.09 50.21 59.04 53.79 44.20 49.05 48.44 54.84 59.37 48.53 50.95 48.26 67.68 53.84 70.78 60.26 64.70 56.15 81.72 63.68 91.26 66.94 80.00 66.00
Li_SMALLRICE_task2_1 LiSMALLRICE2024 58 53.3398550207269 ± 0.001077868702592486 52.83 49.74 50.94 48.53 53.20 51.74 47.76 48.47 44.92 53.79 67.18 51.95 95.80 82.58 43.44 50.32 51.43 52.63 55.34 49.95 65.53 54.42 67.56 59.21 64.12 58.53 76.70 55.26 78.02 52.47 76.52 64.89
Li_SMALLRICE_task2_2 LiSMALLRICE2024 59 53.219453690488216 ± 0.0010799999895663354 52.20 48.74 48.96 48.47 53.46 51.00 48.59 48.68 45.32 53.26 65.87 50.26 96.08 84.00 43.60 50.37 52.60 53.58 55.38 50.84 64.66 55.11 67.30 60.05 65.22 58.79 77.04 56.16 77.04 52.63 77.38 64.95
Li_SMALLRICE_task2_3 LiSMALLRICE2024 53 53.81856456562342 ± 0.0011243926792786517 51.46 50.00 49.04 48.37 54.65 53.74 55.68 49.11 45.79 53.63 65.34 50.16 93.89 74.63 40.74 51.16 56.53 54.68 55.64 49.21 66.26 53.53 66.68 55.42 65.74 57.84 77.52 59.16 69.82 51.47 77.02 65.21
Li_SMALLRICE_task2_4 LiSMALLRICE2024 60 52.8949449499208 ± 0.0010522151699050406 56.40 49.53 50.42 48.32 52.69 51.47 46.53 48.47 43.79 52.84 64.89 50.16 95.54 81.79 43.76 50.11 50.03 51.89 55.16 50.42 65.42 55.21 65.22 59.58 64.70 58.37 74.98 54.32 76.68 52.84 79.60 67.32
Huang_Xju_task2_1 HuangXju2024 46 54.38612240957236 ± 0.001005392973156531 54.05 49.84 58.72 58.63 67.92 52.21 53.68 48.53 57.09 55.00 45.11 50.16 54.60 49.79 62.31 52.89 55.06 49.32 49.89 50.57 49.98 47.68 54.82 59.31 61.59 52.26 73.29 51.94 70.10 48.21 52.55 51.68
Huang_Xju_task2_2 HuangXju2024 55 53.659991099222346 ± 0.0009880937196739639 57.51 48.74 51.31 50.05 60.40 51.16 44.39 48.32 55.47 49.32 43.64 50.11 59.23 50.58 73.18 57.42 65.80 50.79 50.20 47.68 58.68 48.15 63.03 58.42 62.05 57.78 62.07 53.52 59.62 51.00 46.50 50.94
Guo_BIT_task2_1 GuoBIT2024 88 46.96912513794397 ± 0.00097893022763103 46.68 49.26 44.54 48.53 45.94 50.32 33.16 47.89 42.96 53.11 50.70 49.63 65.40 55.21 53.72 51.58 39.32 48.95 46.97 47.58 56.73 49.05 62.46 54.63 56.00 54.11 70.10 58.42 68.03 49.16 63.61 56.95
Guo_BIT_task2_2 GuoBIT2024 76 50.04651414050538 ± 0.0009972105745301837 59.76 57.32 41.74 49.95 45.09 49.42 50.32 49.00 44.69 51.79 50.83 51.21 51.51 51.47 58.08 51.84 49.40 48.79 51.23 48.84 66.14 51.84 63.25 57.00 65.08 56.68 58.57 52.74 70.78 55.05 59.56 50.53
Guo_BIT_task2_3 GuoBIT2024 48 54.084345600639494 ± 0.0010037944335590143 65.66 51.26 59.86 53.84 57.17 50.47 59.52 55.32 52.75 56.79 52.10 52.32 54.94 48.42 53.79 50.16 46.16 49.32 48.16 51.58 59.22 49.16 55.92 59.11 55.92 50.84 81.31 57.79 78.01 58.32 49.28 51.11
Guo_BIT_task2_4 GuoBIT2024 86 48.48349564494921 ± 0.0010170844716108469 49.91 49.58 44.98 48.53 48.39 49.74 34.20 48.37 43.15 52.53 53.43 49.95 65.84 54.53 54.72 53.16 45.59 49.53 51.53 48.84 63.96 49.74 61.93 56.37 56.10 57.11 73.54 57.95 70.24 48.89 64.97 54.68
Wan_HFUU_task2_1 WanHFUU2024 37 56.95741891894512 ± 0.0010154269725155024 62.30 51.63 63.32 51.53 55.72 53.58 55.58 51.26 50.91 55.16 60.41 55.63 64.45 51.89 61.04 53.84 65.54 47.89 51.10 49.20 70.44 52.57 64.40 57.57 62.80 55.42 75.68 54.31 91.74 70.84 76.82 63.21
Wan_HFUU_task2_2 WanHFUU2024 51 54.004134027500136 ± 0.0010180479918878796 60.74 50.79 52.14 48.74 51.93 51.58 56.17 51.68 53.34 56.05 68.16 62.26 55.45 51.63 40.89 49.32 67.67 48.32 48.80 49.36 71.84 55.21 63.20 55.15 70.72 58.78 68.72 54.47 92.28 75.00 73.25 61.47
Wan_HFUU_task2_3 WanHFUU2024 49 54.040077780815054 ± 0.0010321740735709471 51.33 49.84 58.40 56.05 82.19 69.00 54.70 49.47 46.75 51.11 51.53 51.16 45.71 50.37 58.73 49.26 57.92 50.74 53.34 48.89 50.33 47.52 62.11 57.42 78.91 61.10 58.28 58.73 77.33 55.10 55.65 50.78
Wan_HFUU_task2_4 WanHFUU2024 38 56.86467346294555 ± 0.0010054281005031146 57.38 51.42 61.62 57.63 77.14 55.47 57.36 51.84 61.01 53.11 52.15 52.37 56.66 49.32 61.38 53.11 54.99 49.58 50.30 50.47 49.71 47.78 61.36 53.00 77.59 54.36 55.73 59.42 77.12 48.47 51.43 52.94
Kong_IMECAS_task2_1 KongIMECAS2024 42 56.02395073995415 ± 0.001077883896106262 58.38 49.16 59.54 53.47 67.74 56.84 41.24 50.42 52.62 50.26 53.60 51.47 63.83 50.16 74.03 57.21 68.14 50.42 51.78 48.42 62.55 48.31 63.98 57.35 60.86 56.00 69.14 55.32 63.69 53.32 47.24 52.05
Kong_IMECAS_task2_2 KongIMECAS2024 40 56.50382577391263 ± 0.0009983711243153732 55.91 51.16 64.26 60.68 77.64 60.16 59.36 52.05 53.65 53.95 51.42 51.05 52.16 48.47 65.65 53.84 54.09 49.16 49.86 51.21 50.65 47.89 54.30 58.95 60.62 52.05 77.56 54.79 77.83 48.84 52.46 50.74
Kong_IMECAS_task2_3 KongIMECAS2024 45 55.20983600747095 ± 0.0010311321102316356 59.55 49.16 54.27 51.32 66.66 55.53 50.21 51.79 55.56 50.95 54.17 50.16 57.09 50.53 71.92 56.26 50.76 51.74 50.17 48.89 61.16 47.89 60.84 56.11 61.52 58.78 67.97 54.78 58.88 51.05 46.75 51.63
Kong_IMECAS_task2_4 KongIMECAS2024 52 53.84279796938759 ± 0.0010404899494742628 55.32 49.11 59.63 57.26 77.12 59.37 55.66 53.63 52.85 58.42 50.35 51.84 49.78 47.79 61.78 51.53 40.44 49.32 50.43 49.84 51.95 48.26 52.58 59.63 60.09 55.32 75.75 54.68 61.87 48.95 52.88 49.05
Hai_SCU_task2_1 HaiSCU2024 72 50.34153796416583 ± 0.0010155482504932121 57.31 51.00 41.57 47.84 65.33 57.16 54.01 54.53 41.13 47.84 57.91 55.74 49.20 48.58 46.77 49.53 46.16 50.53 49.64 51.21 54.78 48.78 66.57 60.36 51.51 48.95 62.52 50.47 63.18 48.89 51.29 50.94
Kim_DAU_task2_1 KimDAU2024 71 50.433236408626016 ± 0.0010116627475769257 69.05 52.05 46.70 48.32 50.78 49.68 49.59 49.63 57.53 54.21 51.58 50.11 45.57 49.05 46.63 49.42 45.13 50.00 66.83 66.65 62.39 53.43 80.15 70.95 75.95 75.95 73.51 72.32 79.72 71.36 78.03 72.48
Bian_NR_task2_1 BianNR2024 78 49.753503516592126 ± 0.000993616773430831 59.52 62.89 52.98 49.79 58.57 51.26 42.63 49.00 50.48 52.00 49.23 50.89 49.61 48.95 38.07 49.84 46.87 52.05 42.29 50.84 61.04 52.63 61.25 56.47 51.90 50.84 54.74 51.47 51.38 51.31 42.70 48.31
Bian_NR_task2_2 BianNR2024 74 50.30296617352682 ± 0.0009936159397799474 59.33 62.84 52.88 49.74 58.74 51.74 43.64 48.89 51.73 51.68 51.21 50.53 52.51 49.00 38.20 49.95 47.03 51.84 42.45 51.05 61.04 52.63 61.91 56.95 54.52 50.00 54.82 51.63 49.69 50.58 48.06 49.26
Gleichmann_TNT_task2_1 GleichmannTNT2024 93 45.314372753290186 ± 0.0009577819435369494 49.30 49.37 49.06 49.26 48.12 48.63 33.24 48.32 29.82 50.42 48.21 53.37 48.73 50.37 40.46 50.95 55.87 55.37 57.34 50.05 59.56 52.68 62.16 52.32 54.56 51.74 59.38 53.16 73.42 57.74 58.48 49.95
Gleichmann_TNT_task2_2 GleichmannTNT2024 96 43.50109690586943 ± 0.0009591642875581004 49.29 49.79 35.96 47.68 48.40 49.68 38.16 48.95 28.01 50.68 55.30 51.42 29.58 48.21 60.15 52.58 47.03 52.00 55.36 52.32 55.26 53.00 52.46 52.05 50.64 49.37 59.96 52.79 66.54 55.74 60.90 50.26
Gleichmann_TNT_task2_3 GleichmannTNT2024 94 44.5547593776025 ± 0.000975265367338303 48.27 50.32 56.62 52.00 47.60 48.58 34.55 49.00 26.98 49.68 48.13 53.21 49.16 50.79 39.71 49.68 46.08 49.11 57.78 58.16 58.52 53.42 65.06 53.26 54.46 51.00 65.76 51.63 84.00 68.05 63.76 52.89
Gleichmann_TNT_task2_4 GleichmannTNT2024 95 44.2100722208319 ± 0.0009771254966150526 47.18 49.68 40.55 47.58 47.94 51.21 38.79 49.63 43.73 50.26 48.52 54.21 24.28 47.37 56.75 54.00 46.76 51.00 53.70 53.16 55.44 52.89 61.14 54.79 53.48 48.89 59.80 52.94 58.94 50.79 66.12 51.60
Kim_CAU_task2_1 KimCAU2024 89 46.45632996840251 ± 0.0010088781424119019 45.63 50.37 42.38 47.89 42.28 49.16 38.85 51.58 41.32 51.95 56.60 50.53 50.01 50.42 44.30 49.79 46.82 49.11 47.70 49.11 56.48 51.58 60.34 53.26 58.14 57.37 62.30 52.42 77.70 49.53 65.50 56.79
Kim_CAU_task2_2 KimCAU2024 91 46.3583243500304 ± 0.001018651141970712 45.17 50.89 42.42 47.89 42.42 49.11 39.08 50.32 41.00 51.53 56.29 50.53 49.25 50.37 43.40 49.89 48.27 49.11 47.82 49.37 56.36 51.53 60.04 52.79 58.10 57.32 62.30 52.05 77.78 49.74 64.96 57.11
Kim_CAU_task2_3 KimCAU2024 90 46.37806751968737 ± 0.0010220463678257583 45.02 51.26 42.50 47.84 42.72 49.16 39.50 52.11 40.98 51.37 56.25 50.58 48.63 50.37 42.55 49.74 48.72 48.63 47.76 49.37 56.32 51.68 59.96 52.53 58.20 57.53 62.44 52.16 78.06 49.95 64.82 56.95
Kim_CAU_task2_4 KimCAU2024 92 46.02849005921025 ± 0.0010331697243746052 45.10 51.68 42.66 47.84 42.97 49.05 37.87 52.11 40.86 51.32 56.19 50.95 45.00 49.89 42.05 49.74 50.01 49.11 47.86 49.53 56.38 51.68 59.72 51.84 58.22 57.74 62.46 52.11 78.40 50.58 64.64 56.84
Zhang_HEU_task2_1 ZhangHEU2024 54 53.74623090811457 ± 0.001070067273571812 64.76 53.95 56.05 51.32 49.93 49.79 61.59 56.63 50.50 54.42 47.10 50.42 59.50 48.00 58.03 51.79 50.86 50.79 45.17 49.37 61.37 50.05 56.23 58.00 58.81 51.74 81.43 61.05 85.73 78.84 73.25 56.63
Zhang_HEU_task2_2 ZhangHEU2024 87 48.444106656538125 ± 0.0009694084162672815 65.14 53.58 56.64 52.95 48.60 50.11 40.24 51.21 40.21 49.79 49.56 50.95 61.88 48.21 47.95 52.37 33.11 51.63 45.55 49.11 61.97 50.37 59.14 58.95 55.93 52.74 81.66 60.79 87.80 80.26 72.36 53.74
Zhang_HEU_task2_3 ZhangHEU2024 64 52.20859790836647 ± 0.0009854397213407752 68.54 52.42 51.26 49.32 48.98 50.84 52.58 49.42 47.74 52.11 54.77 53.21 58.60 49.95 57.17 50.47 44.28 49.21 50.05 50.26 54.71 48.74 60.71 60.16 59.22 51.26 73.65 53.95 81.74 54.89 70.78 53.58
Zhang_HEU_task2_4 ZhangHEU2024 57 53.35929374681078 ± 0.0010469561116776395 64.76 53.89 56.06 51.53 49.87 49.68 60.70 56.63 50.23 54.47 47.31 50.53 59.62 48.00 57.40 51.84 47.55 50.42 45.16 49.37 61.41 50.05 56.45 58.16 58.67 51.84 81.47 61.00 85.82 79.05 73.24 56.58
Liu_CXL_task2_1 LiuCXL2024 13 60.52026046959108 ± 0.0011605372202239733 54.82 51.37 63.76 60.16 61.91 50.24 64.81 54.53 74.04 53.21 71.15 53.26 78.56 63.24 55.87 50.16 63.70 50.79 58.38 49.43 68.99 54.26 69.94 57.44 57.45 55.74 67.03 52.54 70.32 55.24 79.75 65.69
Liu_CXL_task2_2 LiuCXL2024 21 59.172117290004934 ± 0.0011168767660327198 54.82 51.37 52.47 49.89 61.91 50.24 64.81 54.53 74.04 53.21 71.15 53.26 78.56 63.24 55.87 50.16 63.70 50.79 58.38 49.43 68.99 54.26 69.94 57.44 57.45 55.74 67.03 52.54 70.32 55.24 79.75 65.69
Liu_CXL_task2_3 LiuCXL2024 24 59.0218070376167 ± 0.0010594661091307043 54.82 51.37 63.76 60.16 61.91 50.24 64.81 54.53 74.04 53.21 53.35 48.26 78.56 63.24 55.87 50.16 63.70 50.79 58.38 49.43 68.99 54.26 69.94 57.44 57.45 55.74 67.03 52.54 70.32 55.24 79.75 65.69
Liu_CXL_task2_4 LiuCXL2024 33 57.73888861092491 ± 0.001025927572057755 54.82 51.37 52.47 49.89 61.91 50.24 64.81 54.53 74.04 53.21 53.35 48.26 78.56 63.24 55.87 50.16 63.70 50.79 58.38 49.43 68.99 54.26 69.94 57.44 57.45 55.74 67.03 52.54 70.32 55.24 79.75 65.69
Guan_HEU_task2_1 GuanHEU2024 65 51.85888049113675 ± 0.0010537619556032335 55.73 53.11 56.32 50.47 79.00 59.21 48.13 48.47 63.68 54.26 42.75 52.37 48.94 50.68 42.32 48.32 47.95 49.42 52.85 49.53 60.29 48.47 71.32 57.00 60.63 57.74 68.67 53.53 64.20 59.39 61.56 51.79
Guan_HEU_task2_2 GuanHEU2024 56 53.477174180187916 ± 0.0009972393288512772 68.99 60.63 54.77 51.21 73.32 59.32 59.39 51.21 48.72 53.74 46.66 50.11 48.01 51.42 42.38 47.95 58.21 49.95 56.19 49.21 51.16 49.26 70.88 59.32 62.56 59.32 58.02 51.47 60.61 50.63 62.28 57.05
Guan_HEU_task2_3 GuanHEU2024 44 55.300089187318115 ± 0.0010532303526585441 59.60 50.95 60.97 50.58 59.64 52.74 58.08 49.32 60.01 55.05 59.27 55.95 60.57 52.05 53.97 53.95 45.76 48.47 52.20 49.95 71.00 52.42 62.38 53.05 60.65 55.53 70.11 51.11 89.25 76.26 82.26 67.05
Guan_HEU_task2_4 GuanHEU2024 43 55.56904711277052 ± 0.0010596716564482372 60.80 51.05 61.57 50.42 62.33 53.42 58.52 49.32 60.31 55.63 58.50 56.11 59.44 51.95 54.08 53.32 46.05 48.53 52.52 49.58 70.52 52.32 63.66 53.84 60.77 55.79 70.29 51.42 89.24 76.00 81.29 65.63
Wang_iflytek_task2_1 Wangiflytek2024 11 61.08842633062041 ± 0.0011747355735174372 54.87 51.37 63.72 60.16 78.59 61.05 64.76 54.53 74.08 53.21 71.11 53.26 71.52 51.21 55.83 50.16 63.75 50.79 60.37 51.13 69.31 55.32 71.55 58.90 60.14 57.35 68.38 53.86 72.44 55.67 80.31 67.34
Wang_iflytek_task2_2 Wangiflytek2024 18 59.712505571600985 ± 0.0011445157039559493 54.87 51.37 52.42 49.89 78.59 61.05 64.76 54.53 74.08 53.21 71.11 53.26 71.52 51.21 55.83 50.16 63.75 50.79 60.37 51.13 69.31 55.32 71.55 58.90 60.14 57.35 68.38 53.86 72.44 55.67 80.31 67.34
Wang_iflytek_task2_3 Wangiflytek2024 20 59.5589806638062 ± 0.0011764675312018005 54.87 51.37 63.72 60.16 78.59 61.05 64.76 54.53 74.08 53.21 53.29 48.26 71.52 51.21 55.83 50.16 63.75 50.79 60.37 51.13 69.31 55.32 71.55 58.90 60.14 57.35 68.38 53.86 72.44 55.67 80.31 67.34
Wang_iflytek_task2_4 Wangiflytek2024 31 58.250356207440255 ± 0.001053694692944958 54.87 51.37 52.42 49.89 78.59 61.05 64.76 54.53 74.08 53.21 53.29 48.26 71.52 51.21 55.83 50.16 63.75 50.79 60.37 51.13 69.31 55.32 71.55 58.90 60.14 57.35 68.38 53.86 72.44 55.67 80.31 67.34
Yang_IND_task2_1 YangIND2024 10 61.35410342629337 ± 0.001148839259798822 54.91 51.37 63.77 60.16 73.30 53.00 64.81 54.53 74.03 53.21 71.16 53.26 78.56 63.24 55.78 50.16 63.70 50.79 55.63 47.28 55.48 47.79 52.98 57.09 64.15 54.98 76.33 60.04 75.31 55.65 53.61 49.98
Yang_IND_task2_2 YangIND2024 16 59.96914851321136 ± 0.0011043973012666275 54.91 51.37 52.48 49.89 73.30 53.00 64.81 54.53 74.03 53.21 71.16 53.26 78.56 63.24 55.78 50.16 63.70 50.79 55.63 47.28 55.48 47.79 52.98 57.09 64.15 54.98 76.33 60.04 75.31 55.65 53.61 49.98
Yang_IND_task2_3 YangIND2024 17 59.80546802276297 ± 0.0011182031973053974 54.91 51.37 63.77 60.16 73.30 53.00 64.81 54.53 74.03 53.21 53.25 48.26 78.56 63.24 55.78 50.16 63.70 50.79 55.63 47.28 55.48 47.79 52.98 57.09 64.15 54.98 76.33 60.04 75.31 55.65 53.61 49.98
Yang_IND_task2_4 YangIND2024 29 58.48879568572292 ± 0.001063436501114148 54.91 51.37 52.48 49.89 73.30 53.00 64.81 54.53 74.03 53.21 53.25 48.26 78.56 63.24 55.78 50.16 63.70 50.79 55.63 47.28 55.48 47.79 52.98 57.09 64.15 54.98 76.33 60.04 75.31 55.65 53.61 49.98


Supplementary metrics (recall, precision, and F1 score)

Rank Submission Information Evaluation Dataset
Submission Code Technical
Report
Official
Rank
3DPrinter
(F1 score)
3DPrinter
(Recall)
3DPrinter
(Precision)
AirCompressor
(F1 score)
AirCompressor
(Recall)
AirCompressor
(Precision)
BrushlessMotor
(F1 score)
BrushlessMotor
(Recall)
BrushlessMotor
(Precision)
HairDryer
(F1 score)
HairDryer
(Recall)
HairDryer
(Precision)
HoveringDrone
(F1 score)
HoveringDrone
(Recall)
HoveringDrone
(Precision)
RoboticArm
(F1 score)
RoboticArm
(Recall)
RoboticArm
(Precision)
Scanner
(F1 score)
Scanner
(Recall)
Scanner
(Precision)
ToothBrush
(F1 score)
ToothBrush
(Recall)
ToothBrush
(Precision)
ToyCircuit
(F1 score)
ToyCircuit
(Recall)
ToyCircuit
(Precision)
DCASE2024_baseline_task2_MAHALA DCASE2024baseline2024 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 21.71 14.00 48.28
DCASE2024_baseline_task2_MSE DCASE2024baseline2024 39 66.64 74.68 60.17 53.49 54.11 52.88 66.67 100.00 50.00 62.65 82.02 50.68 61.92 64.86 59.23 66.43 97.96 50.25 65.89 75.34 58.55 66.67 100.00 50.00 70.50 95.83 55.76
Wilkinghoff_FKIE_task2_1 WilkinghoffFKIE2024 62 64.52 71.11 59.04 15.86 10.18 35.90 61.35 80.40 49.60 65.16 83.72 53.33 36.36 27.59 53.33 70.19 97.96 54.68 11.15 7.11 25.81 58.14 66.67 51.55 18.22 11.22 48.50
Wilkinghoff_FKIE_task2_2 WilkinghoffFKIE2024 67 67.80 78.68 59.56 11.21 6.55 39.13 61.85 84.05 48.92 64.15 80.95 53.12 34.15 24.56 56.00 68.82 96.99 53.33 15.46 9.75 37.32 48.00 46.15 50.00 7.18 3.92 42.92
Wilkinghoff_FKIE_task2_3 WilkinghoffFKIE2024 69 66.67 77.54 58.47 15.24 9.60 36.92 63.07 82.70 50.97 64.15 80.95 53.12 39.56 30.51 56.25 68.66 92.73 54.51 15.03 9.43 37.08 55.07 55.07 55.07 13.43 7.68 53.33
Fujimura_NU_task2_1 FujimuraNU2024 26 64.46 58.17 72.28 11.76 6.86 41.38 59.68 68.64 52.80 40.92 29.76 65.46 23.92 14.40 70.59 67.34 100.00 50.76 6.26 3.60 24.00 67.03 69.92 64.38 7.29 3.90 55.71
Fujimura_NU_task2_2 FujimuraNU2024 35 68.54 62.86 75.34 9.58 5.33 47.06 64.86 75.43 56.90 40.55 29.33 65.67 7.15 3.90 43.18 67.56 98.99 51.28 6.36 3.60 27.27 59.96 64.86 55.74 7.16 3.90 43.33
Fujimura_NU_task2_3 FujimuraNU2024 28 60.31 52.81 70.28 13.45 8.00 42.11 56.17 59.68 53.05 44.24 32.00 71.64 31.84 20.65 69.48 67.57 98.99 51.29 6.10 3.50 23.73 65.66 60.42 71.90 7.27 3.89 54.96
Fujimura_NU_task2_4 FujimuraNU2024 27 66.07 60.59 72.64 11.51 6.86 35.82 59.41 64.62 54.97 40.92 29.76 65.46 22.74 13.54 70.97 67.34 100.00 50.76 6.16 3.60 21.43 57.46 47.92 71.74 7.27 3.89 54.81
Zhao_CUMT_task2_1 ZhaoCUMT2024 9 52.89 52.81 52.97 55.65 54.86 56.47 70.06 69.94 70.18 56.28 56.14 56.42 70.00 70.00 70.00 66.00 66.00 66.00 78.59 78.38 78.80 53.90 53.70 54.10 63.62 63.44 63.80
Zhao_CUMT_task2_2 ZhaoCUMT2024 12 52.89 52.81 52.97 55.65 54.86 56.47 70.06 69.94 70.18 56.28 56.14 56.42 70.00 70.00 70.00 66.00 66.00 66.00 78.59 78.38 78.80 53.90 53.70 54.10 63.62 63.44 63.80
Zhao_CUMT_task2_3 ZhaoCUMT2024 15 52.89 52.81 52.97 55.65 54.86 56.47 70.06 69.94 70.18 56.28 56.14 56.42 70.00 70.00 70.00 66.00 66.00 66.00 78.59 78.38 78.80 53.90 53.70 54.10 63.62 63.44 63.80
Zhao_CUMT_task2_4 ZhaoCUMT2024 23 52.89 52.81 52.97 55.65 54.86 56.47 70.06 69.94 70.18 56.28 56.14 56.42 70.00 70.00 70.00 66.00 66.00 66.00 78.59 78.38 78.80 53.90 53.70 54.10 63.62 63.44 63.80
Wang_USTC_task2_1 WangUSTC2024 19 52.14 52.08 52.21 54.51 53.53 55.53 57.53 56.14 59.00 56.28 56.14 56.42 70.00 70.00 70.00 66.00 66.00 66.00 62.86 60.55 65.34 54.96 54.84 55.08 63.62 63.44 63.80
Wang_USTC_task2_2 WangUSTC2024 30 52.14 52.08 52.21 54.51 53.53 55.53 57.53 56.14 59.00 56.28 56.14 56.42 70.00 70.00 70.00 66.00 66.00 66.00 62.86 60.55 65.34 54.96 54.84 55.08 63.62 63.44 63.80
Wang_USTC_task2_3 WangUSTC2024 32 52.14 52.08 52.21 54.51 53.53 55.53 57.53 56.14 59.00 56.28 56.14 56.42 70.00 70.00 70.00 66.00 66.00 66.00 62.86 60.55 65.34 54.96 54.84 55.08 63.62 63.44 63.80
Wang_USTC_task2_4 WangUSTC2024 36 52.14 52.08 52.21 54.51 53.53 55.53 57.53 56.14 59.00 56.28 56.14 56.42 70.00 70.00 70.00 66.00 66.00 66.00 62.86 60.55 65.34 54.96 54.84 55.08 63.62 63.44 63.80
Lee_KNU_task2_1 LeeKNU2024 75 57.11 56.84 57.39 56.00 56.00 56.00 60.24 59.40 61.11 12.68 7.67 36.50 7.27 3.92 50.00 45.39 42.67 48.48 53.70 51.10 56.56 41.47 30.21 66.09 22.77 14.81 49.14
Lee_KNU_task2_2 LeeKNU2024 79 50.04 49.92 50.16 56.69 56.84 56.54 64.22 63.94 64.50 12.85 7.67 39.66 0.00 0.00 0.00 45.39 42.67 48.48 55.17 51.93 58.84 42.84 32.59 62.50 22.61 14.77 48.24
Lee_KNU_task2_3 LeeKNU2024 73 53.93 53.33 54.55 58.00 58.00 58.00 60.00 60.00 60.00 18.09 11.27 45.92 0.00 0.00 0.00 46.14 43.10 49.65 57.46 54.19 61.14 48.23 37.89 66.30 22.40 14.79 46.12
Lee_KNU_task2_4 LeeKNU2024 77 50.94 50.98 50.90 57.64 57.72 57.57 63.28 62.86 63.71 6.76 3.91 24.86 0.00 0.00 0.00 45.39 42.67 48.48 56.14 53.33 59.26 43.53 32.73 64.98 23.30 14.79 54.83
Qian_NIVIC_task2_1 QianNIVIC2024 14 53.33 53.33 53.33 54.51 53.53 55.53 67.14 67.06 67.22 55.84 55.58 56.11 70.97 70.99 70.95 66.00 66.00 66.00 63.44 61.54 65.47 53.86 53.70 54.02 62.70 62.60 62.80
Qian_NIVIC_task2_2 QianNIVIC2024 22 53.33 53.33 53.33 54.51 53.53 55.53 67.14 67.06 67.22 55.84 55.58 56.11 70.97 70.99 70.95 66.00 66.00 66.00 63.44 61.54 65.47 53.86 53.70 54.02 62.70 62.60 62.80
Qian_NIVIC_task2_3 QianNIVIC2024 25 53.33 53.33 53.33 54.51 53.53 55.53 67.14 67.06 67.22 55.84 55.58 56.11 70.97 70.99 70.95 66.00 66.00 66.00 63.44 61.54 65.47 53.86 53.70 54.02 62.70 62.60 62.80
Qian_NIVIC_task2_4 QianNIVIC2024 34 53.33 53.33 53.33 54.51 53.53 55.53 67.14 67.06 67.22 55.84 55.58 56.11 70.97 70.99 70.95 66.00 66.00 66.00 63.44 61.54 65.47 53.86 53.70 54.02 62.70 62.60 62.80
Jiang_CUP_task2_1 JiangCUP2024 81 31.30 21.76 55.74 0.00 0.00 0.00 46.87 42.42 52.35 47.11 41.73 54.10 37.35 27.43 58.54 60.32 68.64 53.81 19.98 12.86 44.78 40.53 30.51 60.36 12.92 7.38 51.61
Jiang_CUP_task2_2 JiangCUP2024 80 32.75 21.91 64.78 10.24 6.22 28.87 46.07 40.98 52.60 40.00 32.00 53.33 26.32 18.11 48.10 61.25 74.99 51.77 10.26 6.22 29.17 23.24 14.81 53.91 17.84 10.71 53.19
Jiang_CUP_task2_3 JiangCUP2024 84 29.55 19.81 58.10 5.80 3.20 30.77 42.75 37.74 49.30 49.51 47.08 52.22 31.17 21.43 57.14 64.43 85.81 51.57 14.18 8.73 37.80 25.72 17.96 45.27 7.04 3.85 41.32
Jiang_CUP_task2_4 JiangCUP2024 82 35.24 24.62 62.02 10.43 6.00 40.00 51.35 50.51 52.21 47.10 44.31 50.26 26.59 18.15 49.75 63.95 77.79 54.29 18.46 12.00 40.00 36.92 27.59 55.79 7.07 3.86 42.19
Jiang_THUEE_task2_1 JiangTHUEE2024 4 56.33 55.52 57.17 60.79 60.59 60.99 63.02 62.98 63.06 61.98 61.71 62.25 68.44 68.64 68.24 64.37 64.62 64.12 86.06 85.58 86.55 61.18 60.39 61.99 62.86 62.86 62.86
Jiang_THUEE_task2_2 JiangTHUEE2024 6 59.77 59.02 60.54 62.00 61.94 62.06 60.99 60.98 61.00 64.38 64.25 64.52 65.09 65.19 64.98 62.64 57.75 68.44 86.06 85.58 86.55 61.33 60.32 62.38 66.93 66.87 66.99
Jiang_THUEE_task2_3 JiangTHUEE2024 7 57.70 56.95 58.48 59.99 59.93 60.05 55.25 54.86 55.65 64.38 64.25 64.52 68.39 68.64 68.14 63.51 63.75 63.28 81.74 81.56 81.92 62.58 60.94 64.31 63.87 63.75 63.99
Jiang_THUEE_task2_4 JiangTHUEE2024 8 57.70 56.95 58.48 59.99 59.93 60.05 55.25 54.86 55.65 64.38 64.25 64.52 68.39 68.64 68.14 67.40 66.27 68.56 81.74 81.56 81.92 62.58 60.94 64.31 63.87 63.75 63.99
Lv_AITHU_task2_1 LvAITHU2024 3 59.11 58.23 60.02 57.80 57.72 57.88 65.57 65.45 65.69 64.62 64.62 64.62 67.65 67.83 67.47 66.38 66.63 66.13 85.01 84.71 85.31 62.05 61.08 63.06 64.00 63.94 64.06
Lv_AITHU_task2_2 LvAITHU2024 5 59.77 59.02 60.54 62.00 61.94 62.06 60.99 60.98 61.00 64.38 64.25 64.52 65.09 65.19 64.98 61.95 62.22 61.67 86.06 85.58 86.55 61.33 60.32 62.38 66.93 66.87 66.99
Lv_AITHU_task2_3 LvAITHU2024 2 59.37 58.23 60.55 59.99 59.93 60.05 66.68 66.63 66.73 65.52 65.19 65.84 66.63 66.53 66.73 64.79 65.03 64.56 91.99 91.83 92.15 57.81 56.73 58.93 63.00 62.98 63.02
Lv_AITHU_task2_4 LvAITHU2024 1 58.46 57.31 59.66 59.97 59.93 60.01 64.86 64.86 64.86 66.41 66.27 66.55 65.88 65.88 65.88 67.17 67.47 66.88 90.02 89.60 90.44 62.44 60.94 64.02 63.98 63.94 64.02
Yin_Midea_task2_1 YinMidea2024 68 40.16 31.87 54.26 27.81 17.68 65.12 47.14 44.68 49.89 62.84 69.49 57.36 26.67 18.18 50.00 66.89 100.00 50.25 14.34 9.00 35.29 41.67 33.33 55.56 18.36 11.20 50.91
Yin_Midea_task2_2 YinMidea2024 63 57.25 50.04 66.88 12.97 8.00 34.29 43.64 38.40 50.53 36.89 27.69 55.21 32.94 24.56 50.00 67.34 100.00 50.76 11.15 7.06 26.55 44.21 37.33 54.19 13.18 7.56 51.52
Yin_Midea_task2_3 YinMidea2024 83 28.21 18.53 59.06 0.00 0.00 0.00 12.98 7.36 54.76 44.98 41.62 48.94 35.56 27.59 50.00 66.44 98.99 50.00 14.12 9.23 30.00 32.34 24.56 47.33 7.08 3.87 41.10
Yin_Midea_task2_4 YinMidea2024 70 32.55 22.50 58.82 5.90 3.33 25.64 23.87 17.06 39.73 40.22 32.20 53.57 30.77 21.43 54.55 66.67 100.00 50.00 15.58 10.00 35.29 40.40 33.33 51.28 7.09 3.88 41.29
Perez_UPV_task2_1 PerezUPV2024 85 67.59 98.00 51.58 66.67 100.00 50.00 66.67 100.00 50.00 63.32 89.29 49.05 66.67 100.00 50.00 42.75 39.07 47.19 16.11 9.60 50.00 66.67 100.00 50.00 65.45 70.87 60.80
Wu_IACAS_task2_1 WuIACAS2024 61 60.12 57.38 63.13 15.38 9.60 38.71 66.60 87.64 53.71 55.84 58.22 53.64 32.94 24.56 50.00 66.69 93.83 51.72 16.09 10.00 41.10 53.69 50.75 56.99 65.48 75.79 57.65
Wu_IACAS_task2_2 WuIACAS2024 50 60.12 57.38 63.13 15.38 9.60 38.71 66.60 87.64 53.71 55.84 58.22 53.64 32.94 24.56 50.00 66.69 93.83 51.72 16.09 10.00 41.10 53.69 50.75 56.99 65.48 75.79 57.65
Wu_IACAS_task2_3 WuIACAS2024 47 60.12 57.38 63.13 15.38 9.60 38.71 66.60 87.64 53.71 55.84 58.22 53.64 32.94 24.56 50.00 66.69 93.83 51.72 16.09 10.00 41.10 53.69 50.75 56.99 65.48 75.79 57.65
Wu_IACAS_task2_4 WuIACAS2024 66 60.12 57.38 63.13 15.38 9.60 38.71 66.60 87.64 53.71 55.84 58.22 53.64 32.94 24.56 50.00 66.69 93.83 51.72 16.09 10.00 41.10 53.69 50.75 56.99 65.48 75.79 57.65
Li_SMALLRICE_task2_1 LiSMALLRICE2024 58 66.61 80.96 56.58 14.04 8.73 35.82 47.90 43.92 52.67 12.55 7.30 44.44 30.77 21.43 54.55 63.68 58.85 69.38 84.64 98.99 73.93 65.82 68.42 63.41 27.45 17.83 59.68
Li_SMALLRICE_task2_2 LiSMALLRICE2024 59 66.44 81.67 56.00 14.10 8.73 36.64 49.05 45.00 53.89 17.66 10.56 53.88 33.73 24.56 53.85 61.63 58.58 65.01 85.37 98.99 75.04 67.07 71.79 62.92 27.53 17.73 61.61
Li_SMALLRICE_task2_3 LiSMALLRICE2024 53 63.38 74.72 55.02 14.10 8.73 36.64 56.93 57.75 56.14 25.42 16.97 50.63 30.77 21.43 54.55 69.46 84.05 59.19 84.07 96.91 74.24 63.69 66.67 60.98 35.29 24.08 66.01
Li_SMALLRICE_task2_4 LiSMALLRICE2024 60 65.17 80.29 54.84 13.59 8.40 35.59 47.91 43.52 53.28 12.41 7.24 43.43 30.77 21.43 54.55 53.60 45.96 64.29 85.35 98.99 75.02 64.43 64.86 64.00 18.71 11.16 57.69
Huang_Xju_task2_1 HuangXju2024 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 66.67 100.00 50.00
Huang_Xju_task2_2 HuangXju2024 55 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 66.89 100.00 50.25 0.00 0.00 0.00
Guo_BIT_task2_1 GuoBIT2024 88 46.93 46.81 47.05 46.00 46.00 46.00 47.85 47.25 48.46 22.17 14.72 44.88 34.52 26.55 49.33 53.86 53.70 54.02 62.85 63.44 62.27 46.74 45.33 48.23 32.10 23.92 48.81
Guo_BIT_task2_2 GuoBIT2024 76 55.38 49.26 63.24 45.28 45.22 45.34 46.82 46.47 47.17 49.64 49.68 49.60 32.86 26.43 43.43 46.97 41.21 54.60 47.02 44.31 50.09 51.01 47.72 54.79 25.20 18.08 41.59
Guo_BIT_task2_3 GuoBIT2024 48 64.22 64.62 63.83 56.08 55.36 56.82 54.72 53.43 56.07 51.62 47.36 56.72 7.28 3.92 50.51 50.00 50.00 50.00 50.71 48.44 53.22 56.52 52.88 60.70 51.72 46.98 57.52
Guo_BIT_task2_4 GuoBIT2024 86 48.79 48.49 49.09 48.76 48.82 48.70 44.89 43.40 46.49 29.53 21.18 48.78 32.62 24.00 50.91 55.40 54.21 56.64 61.76 62.44 61.10 46.72 44.68 48.95 25.00 18.00 40.91
Wan_HFUU_task2_1 WanHFUU2024 37 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 66.67 100.00 50.00
Wan_HFUU_task2_2 WanHFUU2024 51 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 66.67 100.00 50.00
Wan_HFUU_task2_3 WanHFUU2024 49 66.89 100.00 50.25 66.22 98.99 49.75 66.67 100.00 50.00 66.67 100.00 50.00 58.03 63.01 53.78 66.67 100.00 50.00 47.90 47.92 47.88 66.67 100.00 50.00 66.67 100.00 50.00
Wan_HFUU_task2_4 WanHFUU2024 38 0.00 0.00 0.00 66.67 100.00 50.00 66.67 100.00 50.00 14.29 8.00 66.67 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
Kong_IMECAS_task2_1 KongIMECAS2024 42 66.89 98.99 50.52 65.98 96.00 50.26 66.67 100.00 50.00 66.67 100.00 50.00 66.90 97.96 50.79 66.67 98.99 50.26 66.67 100.00 50.00 66.67 100.00 50.00 20.00 12.00 60.00
Kong_IMECAS_task2_2 KongIMECAS2024 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 66.67 100.00 50.00
Kong_IMECAS_task2_3 KongIMECAS2024 45 0.00 0.00 0.00 0.00 0.00 0.00 52.92 46.47 61.45 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
Kong_IMECAS_task2_4 KongIMECAS2024 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 66.67 100.00 50.00
Hai_SCU_task2_1 HaiSCU2024 72 58.01 57.93 58.09 41.13 40.19 42.13 61.03 60.85 61.21 49.52 49.28 49.76 38.54 29.89 54.25 56.00 56.00 56.00 49.06 47.69 50.52 48.51 47.35 49.72 46.33 39.25 56.52
Kim_DAU_task2_1 KimDAU2024 71 65.60 60.98 70.97 26.37 19.09 42.60 56.29 58.41 54.31 40.39 36.71 44.89 53.33 48.48 59.26 57.14 64.86 51.06 16.75 10.67 39.02 47.06 48.48 45.71 48.92 50.75 47.22
Bian_NR_task2_1 BianNR2024 78 46.75 32.24 84.98 0.00 0.00 0.00 32.08 22.61 55.20 11.54 6.55 48.65 12.76 7.27 51.95 32.02 23.74 49.19 21.98 14.44 45.94 43.24 38.71 48.98 48.82 43.56 55.52
Bian_NR_task2_2 BianNR2024 74 46.09 32.94 76.71 16.65 9.43 70.97 25.51 16.42 57.14 16.05 9.60 48.98 21.05 13.33 50.00 41.90 34.32 53.79 40.17 31.54 55.31 50.00 48.48 51.61 58.03 62.61 54.08
Gleichmann_TNT_task2_1 GleichmannTNT2024 93 55.53 65.76 48.06 52.53 54.86 50.39 39.72 30.91 55.56 0.00 0.00 0.00 0.00 0.00 0.00 38.30 36.00 40.91 20.40 13.22 44.71 66.67 100.00 50.00 0.00 0.00 0.00
Gleichmann_TNT_task2_2 GleichmannTNT2024 96 50.57 49.41 51.79 38.10 35.56 41.03 54.68 60.32 50.00 48.98 48.00 50.00 30.56 22.24 48.84 55.48 57.27 53.80 35.61 34.29 37.04 51.30 45.28 59.18 35.97 26.78 54.80
Gleichmann_TNT_task2_3 GleichmannTNT2024 94 53.44 59.40 48.57 56.93 58.17 55.75 25.97 16.67 58.82 0.00 0.00 0.00 68.92 85.61 57.67 37.38 33.48 42.31 32.22 25.44 43.93 36.09 33.22 39.50 56.13 63.55 50.27
Gleichmann_TNT_task2_4 GleichmannTNT2024 95 41.97 38.05 46.79 33.21 27.24 42.53 57.89 67.83 50.49 30.00 21.43 50.00 43.14 39.80 47.09 52.98 57.14 49.38 31.10 28.80 33.80 53.65 50.72 56.95 36.23 26.88 55.54
Kim_CAU_task2_1 KimCAU2024 89 31.19 23.04 48.24 9.88 6.00 27.91 6.59 3.50 56.00 0.00 0.00 0.00 33.23 26.98 43.24 0.00 0.00 0.00 29.82 22.61 43.77 48.89 45.04 53.47 0.00 0.00 0.00
Kim_CAU_task2_2 KimCAU2024 91 30.41 22.50 46.88 10.00 6.00 30.00 6.69 3.56 57.14 0.00 0.00 0.00 33.36 27.08 43.46 0.00 0.00 0.00 29.82 22.61 43.77 47.95 43.64 53.22 0.00 0.00 0.00
Kim_CAU_task2_3 KimCAU2024 90 33.71 25.71 48.91 10.04 6.00 30.77 6.68 3.56 55.17 0.00 0.00 0.00 33.36 27.08 43.46 0.00 0.00 0.00 29.65 22.61 43.05 48.13 43.93 53.22 0.00 0.00 0.00
Kim_CAU_task2_4 KimCAU2024 92 33.40 25.71 47.62 10.04 6.00 30.77 6.79 3.60 60.00 0.00 0.00 0.00 33.30 27.08 43.24 0.00 0.00 0.00 30.27 22.61 45.77 47.99 43.93 52.88 0.00 0.00 0.00
Zhang_HEU_task2_1 ZhangHEU2024 54 57.70 52.08 64.70 51.67 45.96 59.02 36.56 28.96 49.59 46.50 36.71 63.41 0.00 0.00 0.00 35.85 29.47 45.75 20.95 14.44 38.12 56.33 50.08 64.36 28.99 19.64 55.38
Zhang_HEU_task2_2 ZhangHEU2024 87 57.77 52.80 63.77 51.41 45.22 59.56 38.84 29.25 57.78 0.00 0.00 0.00 0.00 0.00 0.00 49.15 44.98 54.18 20.95 14.44 38.12 0.00 0.00 0.00 0.00 0.00 0.00
Zhang_HEU_task2_3 ZhangHEU2024 64 58.32 50.98 68.13 30.00 23.04 42.99 45.40 42.31 48.97 43.48 36.71 53.33 7.14 3.91 40.72 43.75 39.10 49.65 47.10 40.43 56.40 56.89 51.93 62.90 23.85 15.24 54.79
Zhang_HEU_task2_4 ZhangHEU2024 57 64.09 66.27 62.05 54.82 54.00 55.67 45.36 39.25 53.72 52.48 45.00 62.94 18.73 11.31 54.55 48.27 43.52 54.18 54.97 51.47 58.97 58.71 54.62 63.46 37.38 29.52 50.93
Liu_CXL_task2_1 LiuCXL2024 13 52.14 52.08 52.21 55.65 54.86 56.47 57.53 56.14 59.00 55.84 55.58 56.11 70.00 70.00 70.00 66.98 66.99 66.97 78.59 78.38 78.80 54.79 54.55 55.05 62.75 62.60 62.90
Liu_CXL_task2_2 LiuCXL2024 21 52.14 52.08 52.21 55.65 54.86 56.47 57.53 56.14 59.00 55.84 55.58 56.11 70.00 70.00 70.00 66.98 66.99 66.97 78.59 78.38 78.80 54.79 54.55 55.05 62.75 62.60 62.90
Liu_CXL_task2_3 LiuCXL2024 24 52.14 52.08 52.21 55.65 54.86 56.47 57.53 56.14 59.00 55.84 55.58 56.11 70.00 70.00 70.00 66.98 66.99 66.97 78.59 78.38 78.80 54.79 54.55 55.05 62.75 62.60 62.90
Liu_CXL_task2_4 LiuCXL2024 33 52.14 52.08 52.21 55.65 54.86 56.47 57.53 56.14 59.00 55.84 55.58 56.11 70.00 70.00 70.00 66.98 66.99 66.97 78.59 78.38 78.80 54.79 54.55 55.05 62.75 62.60 62.90
Guan_HEU_task2_1 GuanHEU2024 65 55.02 54.84 55.20 53.03 52.98 53.08 68.89 67.94 69.86 49.19 46.59 52.11 56.71 56.56 56.86 43.59 42.31 44.95 48.04 47.92 48.16 28.50 23.74 35.64 36.21 29.65 46.49
Guan_HEU_task2_2 GuanHEU2024 56 63.32 63.44 63.20 52.93 52.53 53.33 71.79 68.05 75.96 55.95 55.93 55.97 35.00 24.37 62.08 46.72 46.47 46.97 42.50 39.67 45.77 33.89 24.23 56.35 56.00 56.00 56.00
Guan_HEU_task2_3 GuanHEU2024 44 60.48 64.62 56.83 57.87 56.14 59.70 53.60 52.81 54.41 49.08 45.71 52.98 51.28 45.00 59.60 50.62 47.08 54.74 49.69 44.41 56.40 41.24 32.16 57.46 30.72 21.33 54.86
Guan_HEU_task2_4 GuanHEU2024 43 59.94 63.44 56.82 58.99 57.38 60.69 55.65 54.86 56.47 50.79 47.72 54.29 54.56 49.35 61.00 50.43 47.08 54.30 48.94 43.52 55.91 43.68 34.69 58.95 34.04 24.37 56.43
Wang_iflytek_task2_1 Wangiflytek2024 11 52.14 52.08 52.21 55.65 54.86 56.47 69.08 68.87 69.29 55.01 54.86 55.17 70.00 70.00 70.00 66.00 66.00 66.00 62.86 60.55 65.34 54.96 54.84 55.08 62.75 62.60 62.90
Wang_iflytek_task2_2 Wangiflytek2024 18 52.14 52.08 52.21 55.65 54.86 56.47 69.08 68.87 69.29 55.01 54.86 55.17 70.00 70.00 70.00 66.00 66.00 66.00 62.86 60.55 65.34 54.96 54.84 55.08 62.75 62.60 62.90
Wang_iflytek_task2_3 Wangiflytek2024 20 52.14 52.08 52.21 55.65 54.86 56.47 69.08 68.87 69.29 55.01 54.86 55.17 70.00 70.00 70.00 66.00 66.00 66.00 62.86 60.55 65.34 54.96 54.84 55.08 62.75 62.60 62.90
Wang_iflytek_task2_4 Wangiflytek2024 31 52.14 52.08 52.21 55.65 54.86 56.47 69.08 68.87 69.29 55.01 54.86 55.17 70.00 70.00 70.00 66.00 66.00 66.00 62.86 60.55 65.34 54.96 54.84 55.08 62.75 62.60 62.90
Yang_IND_task2_1 YangIND2024 10 52.89 52.81 52.97 55.65 54.86 56.47 65.97 65.79 66.15 55.84 55.58 56.11 70.00 70.00 70.00 67.01 66.99 67.03 78.59 78.38 78.80 53.86 53.70 54.02 62.70 62.60 62.80
Yang_IND_task2_2 YangIND2024 16 52.89 52.81 52.97 55.65 54.86 56.47 65.97 65.79 66.15 55.84 55.58 56.11 70.00 70.00 70.00 67.01 66.99 67.03 78.59 78.38 78.80 53.86 53.70 54.02 62.70 62.60 62.80
Yang_IND_task2_3 YangIND2024 17 52.89 52.81 52.97 55.65 54.86 56.47 65.97 65.79 66.15 55.84 55.58 56.11 70.00 70.00 70.00 67.01 66.99 67.03 78.59 78.38 78.80 53.86 53.70 54.02 62.70 62.60 62.80
Yang_IND_task2_4 YangIND2024 29 52.89 52.81 52.97 55.65 54.86 56.47 65.97 65.79 66.15 55.84 55.58 56.11 70.00 70.00 70.00 67.01 66.99 67.03 78.59 78.38 78.80 53.86 53.70 54.02 62.70 62.60 62.80


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)
3DPrinter
(AUC, source)
3DPrinter
(pAUC, source)
AirCompressor
(AUC, source)
AirCompressor
(pAUC, source)
BrushlessMotor
(AUC, source)
BrushlessMotor
(pAUC, source)
HairDryer
(AUC, source)
HairDryer
(pAUC, source)
HoveringDrone
(AUC, source)
HoveringDrone
(pAUC, source)
RoboticArm
(AUC, source)
RoboticArm
(pAUC, source)
Scanner
(AUC, source)
Scanner
(pAUC, source)
ToothBrush
(AUC, source)
ToothBrush
(pAUC, source)
ToyCircuit
(AUC, source)
ToyCircuit
(pAUC, source)
Harmonic mean
(AUC, target)
3DPrinter
(AUC, target)
3DPrinter
(pAUC, target)
AirCompressor
(AUC, target)
AirCompressor
(pAUC, target)
BrushlessMotor
(AUC, target)
BrushlessMotor
(pAUC, target)
HairDryer
(AUC, target)
HairDryer
(pAUC, target)
HoveringDrone
(AUC, target)
HoveringDrone
(pAUC, target)
RoboticArm
(AUC, target)
RoboticArm
(pAUC, target)
Scanner
(AUC, target)
Scanner
(pAUC, target)
ToothBrush
(AUC, target)
ToothBrush
(pAUC, target)
ToyCircuit
(AUC, target)
ToyCircuit
(pAUC, target)
DCASE2024_baseline_task2_MAHALA DCASE2024baseline2024 41 56.489 67.18 75.44 50.84 66.10 60.79 80.32 59.05 60.60 55.11 83.88 58.00 58.34 51.79 56.84 49.26 65.56 48.37 67.94 49.21 51.44 42.40 50.84 55.50 60.79 73.38 59.05 58.98 55.11 46.40 58.00 42.50 51.79 55.50 49.26 57.90 48.37 44.64 49.21
DCASE2024_baseline_task2_MSE DCASE2024baseline2024 39 56.508 71.51 79.12 49.42 65.00 55.47 70.70 55.58 62.24 51.63 86.02 50.21 65.96 51.16 69.16 50.11 75.04 52.74 76.58 50.00 50.58 47.96 49.42 48.24 55.47 63.52 55.58 45.98 51.63 43.88 50.21 41.52 51.16 53.74 50.11 69.48 52.74 52.66 50.00
Wilkinghoff_FKIE_task2_1 WilkinghoffFKIE2024 62 52.463 63.25 81.38 58.74 47.36 48.63 64.54 50.68 81.52 56.32 81.62 53.26 78.88 58.11 68.20 49.16 75.52 52.00 35.34 48.00 44.80 57.10 58.74 61.64 48.63 37.90 50.68 43.84 56.32 29.32 53.26 59.46 58.11 51.48 49.16 28.78 52.00 77.74 48.00
Wilkinghoff_FKIE_task2_2 WilkinghoffFKIE2024 67 51.458 57.30 83.64 54.42 44.18 48.84 50.24 50.84 73.54 56.11 80.06 49.63 76.14 54.32 47.78 49.05 75.82 55.95 34.20 48.05 46.47 54.00 54.42 59.22 48.84 46.00 50.84 48.06 56.11 28.14 49.63 54.18 54.32 51.84 49.05 33.32 55.95 80.60 48.05
Wilkinghoff_FKIE_task2_3 WilkinghoffFKIE2024 69 51.238 58.27 82.84 58.47 43.76 48.79 57.86 51.95 73.96 57.42 81.12 48.95 70.36 53.63 50.88 48.63 81.16 54.37 33.10 48.32 45.11 54.28 58.47 55.78 48.79 45.08 51.95 50.10 57.42 26.12 48.95 51.90 53.63 53.16 48.63 30.94 54.37 81.10 48.32
Fujimura_NU_task2_1 FujimuraNU2024 26 58.899 61.13 83.92 59.79 57.16 49.05 64.48 50.53 58.28 52.68 84.34 53.16 63.38 57.68 66.24 50.37 81.24 56.11 33.22 48.68 63.86 64.86 59.79 64.22 49.05 50.42 50.53 74.76 52.68 54.74 53.16 79.62 57.68 56.28 50.37 63.34 56.11 80.90 48.68
Fujimura_NU_task2_2 FujimuraNU2024 35 57.532 62.09 84.62 60.32 58.94 49.53 69.38 50.21 56.96 51.84 85.72 54.05 64.64 58.16 66.82 50.16 79.18 54.11 33.94 48.47 58.58 64.88 60.32 67.98 49.53 42.90 50.21 75.92 51.84 46.22 54.05 78.08 58.16 57.08 50.16 43.70 54.11 82.08 48.47
Fujimura_NU_task2_3 FujimuraNU2024 28 58.530 59.85 82.50 59.11 55.04 49.05 60.62 50.79 59.62 54.05 82.26 51.21 57.88 55.53 65.06 50.32 83.02 56.68 33.38 49.11 64.28 65.62 59.11 63.24 49.05 52.92 50.79 74.32 54.05 52.12 51.21 81.68 55.53 56.20 50.32 66.64 56.68 80.72 49.11
Fujimura_NU_task2_4 FujimuraNU2024 27 58.874 59.57 83.96 59.21 56.62 49.05 62.08 51.00 56.66 51.89 81.82 54.79 66.50 58.95 66.38 50.11 67.80 55.84 32.60 48.74 65.32 64.34 59.21 60.36 49.05 50.00 51.00 74.06 51.89 62.66 54.79 77.34 58.95 55.54 50.11 78.20 55.84 80.10 48.74
Zhao_CUMT_task2_1 ZhaoCUMT2024 9 61.965 68.65 60.20 51.37 71.34 60.16 83.26 61.05 69.06 54.53 78.96 53.21 73.57 53.26 76.59 63.24 51.33 50.16 65.86 50.79 63.91 50.48 51.37 57.62 60.16 74.48 61.05 61.06 54.53 69.71 53.21 68.72 53.26 80.65 63.24 61.02 50.16 61.88 50.79
Zhao_CUMT_task2_2 ZhaoCUMT2024 12 60.552 65.62 60.20 51.37 49.80 49.89 83.26 61.05 69.06 54.53 78.96 53.21 73.57 53.26 76.59 63.24 51.33 50.16 65.86 50.79 63.60 50.48 51.37 55.43 49.89 74.48 61.05 61.06 54.53 69.71 53.21 68.72 53.26 80.65 63.24 61.02 50.16 61.88 50.79
Zhao_CUMT_task2_3 ZhaoCUMT2024 15 60.399 66.16 60.20 51.37 71.34 60.16 83.26 61.05 69.06 54.53 78.96 53.21 53.96 48.26 76.59 63.24 51.33 50.16 65.86 50.79 61.97 50.48 51.37 57.62 60.16 74.48 61.05 61.06 54.53 69.71 53.21 52.73 48.26 80.65 63.24 61.02 50.16 61.88 50.79
Zhao_CUMT_task2_4 ZhaoCUMT2024 23 59.056 63.34 60.20 51.37 49.80 49.89 83.26 61.05 69.06 54.53 78.96 53.21 53.96 48.26 76.59 63.24 51.33 50.16 65.86 50.79 61.68 50.48 51.37 55.43 49.89 74.48 61.05 61.06 54.53 69.71 53.21 52.73 48.26 80.65 63.24 61.02 50.16 61.88 50.79
Wang_USTC_task2_1 WangUSTC2024 19 59.684 65.73 60.04 51.37 71.32 60.16 54.67 50.24 69.06 54.53 78.92 53.21 73.68 53.26 79.10 51.21 51.52 50.16 65.86 50.79 62.33 50.44 51.37 57.45 60.16 71.33 50.24 61.05 54.53 69.76 53.21 68.63 53.26 65.28 51.21 61.04 50.16 61.87 50.79
Wang_USTC_task2_2 WangUSTC2024 30 58.378 62.94 60.04 51.37 49.80 49.89 54.67 50.24 69.06 54.53 78.92 53.21 73.68 53.26 79.10 51.21 51.52 50.16 65.86 50.79 62.05 50.44 51.37 55.42 49.89 71.33 50.24 61.05 54.53 69.76 53.21 68.63 53.26 65.28 51.21 61.04 50.16 61.87 50.79
Wang_USTC_task2_3 WangUSTC2024 32 58.229 63.43 60.04 51.37 71.32 60.16 54.67 50.24 69.06 54.53 78.92 53.21 53.96 48.26 79.10 51.21 51.52 50.16 65.86 50.79 60.48 50.44 51.37 57.45 60.16 71.33 50.24 61.05 54.53 69.76 53.21 52.72 48.26 65.28 51.21 61.04 50.16 61.87 50.79
Wang_USTC_task2_4 WangUSTC2024 36 56.986 60.83 60.04 51.37 49.80 49.89 54.67 50.24 69.06 54.53 78.92 53.21 53.96 48.26 79.10 51.21 51.52 50.16 65.86 50.79 60.23 50.44 51.37 55.42 49.89 71.33 50.24 61.05 54.53 69.76 53.21 52.72 48.26 65.28 51.21 61.04 50.16 61.87 50.79
Lee_KNU_task2_1 LeeKNU2024 75 50.244 60.63 72.14 52.53 55.22 48.74 46.70 51.11 73.02 49.68 81.18 48.42 34.00 50.79 61.02 48.89 87.48 57.21 84.70 51.53 42.45 49.70 52.53 56.00 48.74 74.98 51.11 28.26 49.68 30.48 48.42 61.72 50.79 54.00 48.89 39.34 57.21 30.90 51.53
Lee_KNU_task2_2 LeeKNU2024 79 49.690 61.44 66.08 49.68 60.54 48.21 47.80 50.79 69.64 49.21 80.68 48.79 33.98 51.26 69.74 49.53 87.36 54.79 83.74 51.84 41.23 47.20 49.68 48.72 48.21 77.84 50.79 25.70 49.21 29.56 48.79 61.86 51.26 56.50 49.53 36.62 54.79 33.56 51.84
Lee_KNU_task2_3 LeeKNU2024 73 50.316 63.12 68.52 49.68 61.04 48.11 58.38 50.95 70.10 49.74 81.68 49.00 33.08 51.05 69.70 49.32 87.06 55.16 83.94 50.63 41.82 45.28 49.68 49.28 48.11 69.78 50.95 28.10 49.74 29.32 49.00 61.80 51.05 59.36 49.32 38.56 55.16 33.50 50.63
Lee_KNU_task2_4 LeeKNU2024 77 49.759 61.20 64.56 49.47 60.14 48.37 49.02 50.84 69.64 49.21 79.50 49.11 33.54 51.26 69.32 49.47 87.20 55.63 84.08 51.74 41.42 47.42 49.47 49.00 48.37 77.58 50.84 25.02 49.21 30.14 49.11 61.78 51.26 56.06 49.47 37.74 55.63 34.20 51.74
Qian_NIVIC_task2_1 QianNIVIC2024 14 60.498 68.27 60.22 51.37 71.32 60.16 75.84 53.00 69.06 54.53 79.02 53.21 73.60 53.26 79.10 51.21 51.46 50.16 65.73 50.79 62.30 50.46 51.37 57.46 60.16 71.12 53.00 61.03 54.53 69.86 53.21 68.72 53.26 65.28 51.21 60.90 50.16 61.80 50.79
Qian_NIVIC_task2_2 QianNIVIC2024 22 59.147 65.24 60.22 51.37 49.64 49.89 75.84 53.00 69.06 54.53 79.02 53.21 73.60 53.26 79.10 51.21 51.46 50.16 65.73 50.79 62.02 50.46 51.37 55.38 49.89 71.12 53.00 61.03 54.53 69.86 53.21 68.72 53.26 65.28 51.21 60.90 50.16 61.80 50.79
Qian_NIVIC_task2_3 QianNIVIC2024 25 59.003 65.80 60.22 51.37 71.32 60.16 75.84 53.00 69.06 54.53 79.02 53.21 53.96 48.26 79.10 51.21 51.46 50.16 65.73 50.79 60.46 50.46 51.37 57.46 60.16 71.12 53.00 61.03 54.53 69.86 53.21 52.72 48.26 65.28 51.21 60.90 50.16 61.80 50.79
Qian_NIVIC_task2_4 QianNIVIC2024 34 57.717 62.98 60.22 51.37 49.64 49.89 75.84 53.00 69.06 54.53 79.02 53.21 53.96 48.26 79.10 51.21 51.46 50.16 65.73 50.79 60.19 50.46 51.37 55.38 49.89 71.12 53.00 61.03 54.53 69.86 53.21 52.72 48.26 65.28 51.21 60.90 50.16 61.80 50.79
Jiang_CUP_task2_1 JiangCUP2024 81 49.490 54.57 60.70 51.84 45.04 48.11 58.70 51.00 64.74 49.84 75.10 48.32 64.78 51.53 55.30 48.32 80.50 50.05 28.98 48.21 45.14 68.40 51.84 58.92 48.11 48.66 51.00 44.38 49.84 27.20 48.32 52.38 51.53 52.28 48.32 26.76 50.05 81.00 48.21
Jiang_CUP_task2_2 JiangCUP2024 80 49.542 53.22 51.52 53.32 44.22 48.68 54.62 49.53 63.20 49.32 74.74 48.21 59.08 51.00 50.88 48.32 79.28 49.37 32.92 47.89 46.41 60.44 53.32 57.50 48.68 49.40 49.53 47.76 49.32 29.66 48.21 44.24 51.00 52.12 48.32 33.14 49.37 76.08 47.89
Jiang_CUP_task2_3 JiangCUP2024 84 49.000 51.40 51.90 49.21 46.06 48.42 49.42 50.79 66.44 49.95 81.64 47.37 64.14 51.32 48.54 48.16 75.54 51.53 26.92 48.32 46.44 68.86 49.21 58.24 48.42 53.64 50.79 39.14 49.95 27.32 47.37 49.64 51.32 49.70 48.16 35.72 51.53 76.72 48.32
Jiang_CUP_task2_4 JiangCUP2024 82 49.222 54.03 53.66 51.05 46.04 48.89 61.78 48.79 64.94 49.00 75.24 50.84 66.40 51.63 56.19 48.47 83.28 51.42 27.42 47.84 44.78 67.24 51.05 57.56 48.89 40.96 48.79 39.18 49.00 28.56 50.84 50.74 51.63 45.00 48.47 33.86 51.42 81.02 47.84
Jiang_THUEE_task2_1 JiangTHUEE2024 4 65.369 69.56 62.52 53.53 69.88 53.37 63.56 53.79 73.32 54.63 66.84 57.74 64.82 57.16 96.74 76.89 70.96 54.89 67.16 52.95 72.34 67.18 53.53 66.80 53.37 72.70 53.79 66.62 54.63 80.92 57.74 82.76 57.16 89.66 76.89 64.28 54.89 68.28 52.95
Jiang_THUEE_task2_2 JiangTHUEE2024 6 64.542 67.00 64.44 53.63 64.62 52.89 66.50 54.63 74.46 54.16 66.18 59.63 49.28 53.63 96.74 76.89 69.50 56.16 67.84 52.47 72.35 64.04 53.63 64.92 52.89 67.70 54.63 70.56 54.16 82.08 59.63 85.76 53.63 89.66 76.89 67.10 56.16 68.78 52.47
Jiang_THUEE_task2_3 JiangTHUEE2024 7 64.165 68.65 62.54 53.32 68.24 53.16 61.00 53.68 73.72 54.21 66.92 57.68 62.50 54.68 90.20 58.26 73.20 55.53 67.50 51.95 72.00 66.04 53.32 66.36 53.16 68.72 53.68 67.62 54.21 82.24 57.68 83.06 54.68 86.84 58.26 66.20 55.53 68.40 51.95
Jiang_THUEE_task2_4 JiangTHUEE2024 8 63.967 67.69 62.54 53.32 68.24 53.16 61.00 53.68 73.72 54.21 66.92 57.68 56.00 54.68 90.20 58.26 73.20 55.53 67.50 51.95 72.32 66.04 53.32 66.36 53.16 68.72 53.68 67.62 54.21 82.24 57.68 87.06 54.68 86.84 58.26 66.20 55.53 68.40 51.95
Lv_AITHU_task2_1 LvAITHU2024 3 65.974 70.29 65.50 55.74 67.14 54.21 70.56 56.11 74.88 54.95 68.04 57.95 62.44 54.68 96.82 76.26 68.88 55.79 67.60 53.26 72.91 67.72 55.74 64.96 54.21 71.88 56.11 70.28 54.95 81.76 57.95 82.42 54.68 89.86 76.26 66.20 55.79 68.76 53.26
Lv_AITHU_task2_2 LvAITHU2024 5 64.958 68.72 64.44 53.63 64.62 52.89 66.50 54.63 74.46 54.16 66.18 59.63 59.08 53.68 96.74 76.89 69.50 56.16 67.84 52.47 71.94 64.04 53.63 64.92 52.89 67.70 54.63 70.56 54.16 82.08 59.63 80.90 53.68 89.66 76.89 67.10 56.16 68.78 52.47
Lv_AITHU_task2_3 LvAITHU2024 2 66.169 70.77 66.40 57.32 67.16 50.63 71.76 54.05 75.38 56.21 69.38 56.58 63.68 55.53 96.64 82.26 70.04 57.42 65.42 51.89 73.26 68.74 57.32 63.30 50.63 75.50 54.05 70.20 56.21 79.24 56.58 83.62 55.53 93.18 82.26 67.94 57.42 66.72 51.89
Lv_AITHU_task2_4 LvAITHU2024 1 66.241 71.03 67.80 56.11 65.66 50.84 67.46 54.05 74.82 54.79 69.54 56.84 63.60 54.58 98.10 79.26 74.44 59.74 67.54 52.11 73.66 68.34 56.11 64.12 50.84 71.16 54.05 71.54 54.79 80.76 56.84 85.36 54.58 91.88 79.26 70.38 59.74 67.84 52.11
Yin_Midea_task2_1 YinMidea2024 68 51.364 55.02 56.68 51.95 59.72 50.47 41.82 50.32 57.34 51.58 77.12 51.79 75.72 51.74 53.53 48.74 79.17 50.79 32.94 51.58 48.51 48.38 51.95 64.88 50.47 60.02 50.32 58.04 51.58 31.34 51.79 53.56 51.74 51.76 48.74 30.26 50.79 79.38 51.58
Yin_Midea_task2_2 YinMidea2024 63 52.236 52.54 69.26 50.68 47.56 48.32 43.51 51.21 55.74 51.95 76.32 54.42 67.52 60.21 51.94 48.79 73.90 48.79 29.22 51.47 52.64 56.54 50.68 61.96 48.32 61.66 51.21 69.36 51.95 33.80 54.42 67.80 60.21 51.78 48.79 32.98 48.79 79.74 51.47
Yin_Midea_task2_3 YinMidea2024 83 49.081 48.54 60.12 51.00 45.46 48.58 37.96 53.47 53.04 49.89 74.32 53.16 61.74 52.05 49.46 48.68 77.38 51.79 25.78 48.95 48.01 56.18 51.00 60.80 48.58 70.70 53.47 46.30 49.89 31.42 53.16 52.56 52.05 45.82 48.68 31.12 51.79 78.96 48.95
Yin_Midea_task2_4 YinMidea2024 70 50.606 50.73 55.46 50.63 45.54 48.79 33.86 52.58 58.06 52.95 77.42 53.58 69.46 56.74 57.82 49.32 80.86 50.00 29.68 48.58 49.77 52.10 50.63 64.48 48.79 64.20 52.58 61.02 52.95 32.58 53.58 62.42 56.74 60.26 49.32 26.12 50.00 79.66 48.58
Perez_UPV_task2_1 PerezUPV2024 85 48.984 56.91 56.91 51.13 45.68 49.16 53.85 49.74 58.09 48.23 66.43 49.83 45.23 49.66 52.08 50.01 68.53 51.63 83.67 54.98 41.95 50.66 51.13 49.70 49.16 47.91 49.74 31.27 48.23 30.46 49.83 53.85 49.66 47.23 50.01 32.67 51.63 53.61 54.98
Wu_IACAS_task2_1 WuIACAS2024 61 52.501 67.33 79.34 54.37 49.72 48.37 81.58 50.37 67.12 49.37 85.68 52.00 84.28 52.63 50.02 49.05 85.36 50.32 53.88 47.89 44.54 50.78 54.37 64.74 48.37 31.96 50.37 43.64 49.37 38.30 52.00 52.04 52.63 50.10 49.05 29.50 50.32 73.92 47.89
Wu_IACAS_task2_2 WuIACAS2024 50 54.024 69.09 76.14 52.32 48.38 48.47 83.56 51.79 67.72 49.16 84.74 50.79 82.20 54.32 77.60 50.95 82.62 51.95 48.14 48.26 46.77 51.28 52.32 64.76 48.47 37.22 51.79 42.26 49.16 36.94 50.79 54.30 54.32 66.36 50.95 29.58 51.95 79.48 48.26
Wu_IACAS_task2_3 WuIACAS2024 47 54.169 67.76 76.30 53.47 49.12 48.47 81.62 51.21 65.66 48.63 84.96 51.95 79.96 55.00 67.62 49.68 83.28 50.89 48.08 47.89 47.84 51.78 53.47 64.86 48.47 38.24 51.21 45.44 48.63 38.02 51.95 57.04 55.00 66.20 49.68 29.58 50.89 80.12 47.89
Wu_IACAS_task2_4 WuIACAS2024 66 51.777 64.68 77.60 54.68 47.56 49.32 82.52 52.16 71.26 49.53 74.72 50.21 71.34 53.79 44.76 49.05 80.62 54.84 59.02 48.53 43.55 51.00 54.68 61.48 49.32 39.02 52.16 36.14 49.53 34.38 50.21 50.36 53.79 43.66 49.05 34.62 54.84 59.72 48.53
Li_SMALLRICE_task2_1 LiSMALLRICE2024 58 53.340 56.95 73.54 49.74 45.58 48.53 65.40 51.74 36.04 48.47 81.10 53.79 54.58 51.95 98.16 82.58 88.56 50.32 36.58 52.63 50.38 41.22 49.74 57.72 48.53 44.84 51.74 70.78 48.47 31.06 53.79 87.34 51.95 93.56 82.58 28.78 50.32 86.56 52.63
Li_SMALLRICE_task2_2 LiSMALLRICE2024 59 53.219 56.85 73.52 48.74 44.22 48.47 63.70 51.00 36.76 48.68 81.00 53.26 53.28 50.26 97.78 84.00 87.80 50.37 37.78 53.58 50.38 40.46 48.74 54.84 48.47 46.06 51.00 71.64 48.68 31.46 53.26 86.26 50.26 94.44 84.00 29.00 50.37 86.54 53.58
Li_SMALLRICE_task2_3 LiSMALLRICE2024 53 53.819 62.45 77.66 50.00 47.00 48.37 70.00 53.74 47.70 49.11 79.84 53.63 58.22 50.16 96.88 74.63 87.44 51.16 43.02 54.68 47.84 38.48 50.00 51.26 48.37 44.82 53.74 66.86 49.11 32.10 53.63 74.44 50.16 91.08 74.63 26.56 51.16 82.42 54.68
Li_SMALLRICE_task2_4 LiSMALLRICE2024 60 52.895 55.88 73.50 49.53 45.32 48.32 66.10 51.47 34.68 48.47 80.88 52.84 52.12 50.16 97.72 81.79 88.00 50.11 35.36 51.89 50.53 45.76 49.53 56.82 48.32 43.80 51.47 70.66 48.47 30.02 52.84 85.94 50.16 93.46 81.79 29.12 50.11 85.48 51.89
Huang_Xju_task2_1 HuangXju2024 46 54.386 65.02 61.82 49.84 60.00 58.63 78.00 52.21 55.24 48.53 84.30 55.00 75.40 50.16 55.16 49.79 66.22 52.89 61.38 49.32 48.97 48.02 49.84 57.50 58.63 60.14 52.21 52.20 48.53 43.16 55.00 32.18 50.16 54.06 49.79 58.84 52.89 49.92 49.32
Huang_Xju_task2_2 HuangXju2024 55 53.660 70.18 68.26 48.74 62.58 50.05 64.56 51.16 56.62 48.32 85.20 49.32 73.22 50.11 70.58 50.58 83.28 57.42 77.54 50.79 45.67 49.68 48.74 43.48 50.05 56.74 51.16 36.50 48.32 41.12 49.32 31.08 50.11 51.02 50.58 65.26 57.42 57.14 50.79
Guo_BIT_task2_1 GuoBIT2024 88 46.969 55.04 51.98 49.26 48.52 48.53 39.52 50.32 66.58 47.89 70.44 53.11 53.14 49.63 53.40 55.21 53.90 51.58 76.66 48.95 38.67 42.36 49.26 41.16 48.53 54.86 50.32 22.08 47.89 30.90 53.11 48.48 49.63 84.34 55.21 53.54 51.58 26.44 48.95
Guo_BIT_task2_2 GuoBIT2024 76 50.047 62.08 83.66 57.32 43.78 49.95 55.72 49.42 55.43 49.00 67.52 51.79 75.28 51.21 60.50 51.47 61.50 51.84 75.10 48.79 41.22 46.48 57.32 39.88 49.95 37.86 49.42 46.08 49.00 33.40 51.79 38.37 51.21 44.84 51.47 55.02 51.84 36.80 48.79
Guo_BIT_task2_3 GuoBIT2024 48 54.084 70.22 84.46 51.26 70.74 53.84 66.96 50.47 75.00 55.32 84.44 56.79 54.80 52.32 56.78 48.42 74.80 50.16 77.78 49.32 45.57 53.70 51.26 51.88 53.84 49.88 50.47 49.34 55.32 38.36 56.79 49.66 52.32 53.22 48.42 42.00 50.16 32.82 49.32
Guo_BIT_task2_4 GuoBIT2024 86 48.483 59.91 59.94 49.58 48.54 48.53 49.46 49.74 67.36 48.37 72.34 52.53 67.64 49.95 54.14 54.53 56.24 53.16 76.76 49.53 39.35 42.76 49.58 41.90 48.53 47.36 49.74 22.92 48.37 30.74 52.53 44.16 49.95 83.98 54.53 53.28 53.16 32.42 49.53
Wan_HFUU_task2_1 WanHFUU2024 37 56.957 67.34 70.90 51.63 60.40 51.53 57.64 53.58 73.20 51.26 83.92 55.16 56.88 55.63 74.56 51.89 79.66 53.84 60.52 47.89 53.38 55.56 51.63 66.54 51.53 53.92 53.58 44.80 51.26 36.54 55.16 64.40 55.63 56.76 51.89 49.48 53.84 71.48 47.89
Wan_HFUU_task2_2 WanHFUU2024 51 54.004 65.55 69.12 50.79 47.80 48.74 55.36 51.58 76.72 51.68 82.48 56.05 67.96 62.26 67.40 51.63 76.98 49.32 61.96 48.32 47.50 54.18 50.79 57.34 48.74 48.90 51.58 44.30 51.68 39.42 56.05 68.36 62.26 47.10 51.63 27.84 49.32 74.54 48.32
Wan_HFUU_task2_3 WanHFUU2024 49 54.040 65.03 69.46 49.84 69.46 56.05 88.64 69.00 71.26 49.47 79.12 51.11 62.48 51.16 41.12 50.37 71.64 49.26 57.60 50.74 47.46 40.70 49.84 50.38 56.05 76.62 69.00 44.38 49.47 33.18 51.11 43.84 51.16 51.46 50.37 49.76 49.26 58.24 50.74
Wan_HFUU_task2_4 WanHFUU2024 38 56.865 61.25 65.86 51.42 57.58 57.63 79.40 55.47 53.04 51.84 80.00 53.11 47.54 52.37 60.98 49.32 59.54 53.11 61.72 49.58 57.49 50.84 51.42 66.28 57.63 75.00 55.47 62.44 51.84 49.30 53.11 57.74 52.37 52.92 49.32 63.34 53.11 49.58 49.58
Kong_IMECAS_task2_1 KongIMECAS2024 42 56.024 71.10 78.36 49.16 60.62 53.47 76.84 56.84 75.98 50.42 87.42 50.26 55.14 51.47 70.78 50.16 72.46 57.21 73.30 50.42 49.36 46.52 49.16 58.50 53.47 60.56 56.84 28.30 50.42 37.64 50.26 52.14 51.47 58.12 50.16 75.66 57.21 63.66 50.42
Kong_IMECAS_task2_2 KongIMECAS2024 40 56.504 65.62 73.68 51.16 64.10 60.68 81.10 60.16 68.76 52.05 87.40 53.95 49.48 51.05 54.18 48.47 64.90 53.84 64.18 49.16 52.58 45.04 51.16 64.42 60.68 74.46 60.16 52.22 52.05 38.70 53.95 53.52 51.05 50.28 48.47 66.42 53.84 46.74 49.16
Kong_IMECAS_task2_3 KongIMECAS2024 45 55.210 71.15 74.54 49.16 63.90 51.32 70.22 55.53 63.68 51.79 83.30 50.95 62.84 50.16 68.82 50.53 76.34 56.26 83.74 51.74 47.64 49.58 49.16 47.16 51.32 63.44 55.53 41.44 51.79 41.68 50.95 47.60 50.16 48.78 50.53 67.98 56.26 36.42 51.74
Kong_IMECAS_task2_4 KongIMECAS2024 52 53.843 66.47 75.06 49.11 63.58 57.26 82.20 59.37 61.28 53.63 77.18 58.42 58.32 51.84 48.78 47.79 69.26 51.53 78.00 49.32 45.98 43.80 49.11 56.14 57.26 72.64 59.37 50.98 53.63 40.18 58.42 44.30 51.84 50.82 47.79 55.76 51.53 27.30 49.32
Hai_SCU_task2_1 HaiSCU2024 72 50.342 56.72 54.42 51.00 36.20 47.84 59.18 57.16 54.52 54.53 73.46 47.84 62.42 55.74 53.80 48.58 63.24 49.53 74.68 50.53 44.57 60.52 51.00 48.80 47.84 72.90 57.16 53.50 54.53 28.56 47.84 54.00 55.74 45.32 48.58 37.10 49.53 33.40 50.53
Kim_DAU_task2_1 KimDAU2024 71 50.433 54.64 70.18 52.05 41.25 48.32 57.74 49.68 52.04 49.63 73.08 54.21 58.70 50.11 47.64 49.05 50.38 49.42 55.16 50.00 47.01 67.96 52.05 53.80 48.32 45.32 49.68 47.36 49.63 47.43 54.21 46.00 50.11 43.67 49.05 43.40 49.42 38.18 50.00
Bian_NR_task2_1 BianNR2024 78 49.754 53.40 59.90 62.89 50.40 49.79 61.08 51.26 30.52 49.00 42.06 52.00 69.46 50.89 57.00 48.95 68.90 49.84 79.10 52.05 45.08 59.14 62.89 55.84 49.79 56.26 51.26 70.66 49.00 63.10 52.00 38.12 50.89 43.92 48.95 26.30 49.84 33.30 52.05
Bian_NR_task2_2 BianNR2024 74 50.303 54.13 59.28 62.84 50.40 49.74 59.30 51.74 31.48 48.89 44.76 51.68 67.82 50.53 58.86 49.00 70.48 49.95 79.00 51.84 45.96 59.38 62.84 55.62 49.74 58.20 51.74 71.12 48.89 61.26 51.68 41.14 50.53 47.40 49.00 26.20 49.95 33.48 51.84
Gleichmann_TNT_task2_1 GleichmannTNT2024 93 45.314 37.58 47.04 49.37 41.48 49.26 70.60 48.63 21.72 48.32 18.36 50.42 59.46 53.37 53.86 50.37 41.82 50.95 49.62 55.37 50.44 51.78 49.37 60.04 49.26 36.50 48.63 70.74 48.32 79.28 50.42 40.54 53.37 44.50 50.37 39.18 50.95 63.92 55.37
Gleichmann_TNT_task2_2 GleichmannTNT2024 96 43.501 32.71 48.16 49.79 27.84 47.68 41.30 49.68 26.14 48.95 17.00 50.68 45.30 51.42 23.00 48.21 55.70 52.58 73.40 52.00 54.29 50.48 49.79 50.78 47.68 58.46 49.68 70.64 48.95 79.44 50.68 70.96 51.42 41.42 48.21 65.38 52.58 34.60 52.00
Gleichmann_TNT_task2_3 GleichmannTNT2024 94 44.555 37.60 47.04 50.32 54.50 52.00 67.16 48.58 22.26 49.00 16.02 49.68 59.30 53.21 47.00 50.79 39.14 49.68 72.18 49.11 48.02 49.56 50.32 58.92 52.00 36.86 48.58 77.14 49.00 85.46 49.68 40.50 53.21 51.52 50.79 40.30 49.68 33.84 49.11
Gleichmann_TNT_task2_4 GleichmannTNT2024 95 44.210 38.90 45.78 49.68 31.94 47.58 36.44 51.21 73.70 49.63 51.80 50.26 37.22 54.21 17.52 47.37 50.00 54.00 71.68 51.00 44.79 48.66 49.68 55.52 47.58 70.04 51.21 26.32 49.63 37.84 50.26 69.66 54.21 39.56 47.37 65.60 54.00 34.70 51.00
Kim_CAU_task2_1 KimCAU2024 89 46.456 43.52 60.04 50.37 49.16 47.89 31.88 49.16 26.48 51.58 61.78 51.95 46.90 50.53 47.30 50.42 68.82 49.79 36.38 49.11 46.25 36.80 50.37 37.24 47.89 62.76 49.16 72.92 51.58 31.04 51.95 71.36 50.53 53.04 50.42 32.66 49.79 65.66 49.11
Kim_CAU_task2_2 KimCAU2024 91 46.358 43.83 60.38 50.89 49.00 47.89 32.00 49.11 26.74 50.32 61.86 51.53 46.46 50.53 46.46 50.37 70.54 49.89 37.96 49.11 45.72 36.08 50.89 37.40 47.89 62.90 49.11 72.54 50.32 30.66 51.53 71.40 50.53 52.40 50.37 31.34 49.89 66.26 49.11
Kim_CAU_task2_3 KimCAU2024 90 46.378 44.08 60.76 51.26 49.08 47.84 32.30 49.16 27.18 52.11 62.08 51.37 46.38 50.58 45.70 50.37 71.22 49.74 38.46 48.63 45.39 35.76 51.26 37.48 47.84 63.06 49.16 72.28 52.11 30.58 51.37 71.46 50.58 51.96 50.37 30.34 49.74 66.44 48.63
Kim_CAU_task2_4 KimCAU2024 92 46.028 43.49 61.80 51.68 49.02 47.84 32.48 49.05 25.70 52.11 62.22 51.32 46.28 50.95 41.70 49.89 71.26 49.74 40.02 49.11 44.96 35.50 51.68 37.76 47.84 63.46 49.05 71.92 52.11 30.42 51.32 71.50 50.95 48.86 49.89 29.82 49.74 66.66 49.11
Zhang_HEU_task2_1 ZhangHEU2024 54 53.746 72.32 77.62 53.95 65.48 51.32 69.80 49.79 75.14 56.63 83.92 54.42 65.36 50.42 69.08 48.00 73.98 51.79 74.38 50.79 44.09 55.56 53.95 49.00 51.32 38.86 49.79 52.18 56.63 36.12 54.42 36.82 50.42 52.26 48.00 47.74 51.79 38.64 50.79
Zhang_HEU_task2_2 ZhangHEU2024 87 48.444 71.86 76.16 53.58 64.20 52.95 70.20 50.11 79.66 51.21 86.22 49.79 52.04 50.95 67.60 48.21 85.36 52.37 80.56 51.63 35.14 56.90 53.58 50.68 52.95 37.16 50.11 26.92 51.21 26.22 49.79 47.30 50.95 57.06 48.21 33.34 52.37 20.84 51.63
Zhang_HEU_task2_3 ZhangHEU2024 64 52.209 61.65 80.24 52.42 52.58 49.32 40.48 50.84 66.30 49.42 78.92 52.11 51.56 53.21 62.70 49.95 73.90 50.47 75.90 49.21 46.45 59.82 52.42 50.00 49.32 62.00 50.84 43.56 49.42 34.22 52.11 58.40 53.21 55.00 49.95 46.62 50.47 31.26 49.21
Zhang_HEU_task2_4 ZhangHEU2024 57 53.359 72.66 77.50 53.89 65.32 51.53 69.78 49.68 75.54 56.63 84.02 54.47 64.74 50.53 69.00 48.00 75.56 51.84 76.86 50.42 43.21 55.62 53.89 49.10 51.53 38.80 49.68 50.74 56.63 35.82 54.47 37.28 50.53 52.48 48.00 46.28 51.84 34.42 50.42
Liu_CXL_task2_1 LiuCXL2024 13 60.520 65.53 60.04 51.37 71.34 60.16 54.68 50.24 69.06 54.53 78.96 53.21 73.72 53.26 76.58 63.24 51.50 50.16 65.82 50.79 63.63 50.44 51.37 57.63 60.16 71.35 50.24 61.06 54.53 69.69 53.21 68.76 53.26 80.65 63.24 61.04 50.16 61.71 50.79
Liu_CXL_task2_2 LiuCXL2024 21 59.172 62.76 60.04 51.37 49.80 49.89 54.68 50.24 69.06 54.53 78.96 53.21 73.72 53.26 76.58 63.24 51.50 50.16 65.82 50.79 63.32 50.44 51.37 55.45 49.89 71.35 50.24 61.06 54.53 69.69 53.21 68.76 53.26 80.65 63.24 61.04 50.16 61.71 50.79
Liu_CXL_task2_3 LiuCXL2024 24 59.022 63.24 60.04 51.37 71.34 60.16 54.68 50.24 69.06 54.53 78.96 53.21 53.96 48.26 76.58 63.24 51.50 50.16 65.82 50.79 61.70 50.44 51.37 57.63 60.16 71.35 50.24 61.06 54.53 69.69 53.21 52.75 48.26 80.65 63.24 61.04 50.16 61.71 50.79
Liu_CXL_task2_4 LiuCXL2024 33 57.739 60.66 60.04 51.37 49.80 49.89 54.68 50.24 69.06 54.53 78.96 53.21 53.96 48.26 76.58 63.24 51.50 50.16 65.82 50.79 61.41 50.44 51.37 55.45 49.89 71.35 50.24 61.06 54.53 69.69 53.21 52.75 48.26 80.65 63.24 61.04 50.16 61.71 50.79
Guan_HEU_task2_1 GuanHEU2024 65 51.859 47.35 53.34 53.11 59.78 50.47 76.24 59.21 38.26 48.47 62.32 54.26 39.24 52.37 56.54 50.68 33.66 48.32 37.84 49.42 57.61 58.34 53.11 53.24 50.47 81.96 59.21 64.86 48.47 65.10 54.26 46.96 52.37 43.14 50.68 56.98 48.32 65.42 49.42
Guan_HEU_task2_2 GuanHEU2024 56 53.477 64.76 77.38 60.63 59.66 51.21 88.30 59.32 60.58 51.21 79.84 53.74 44.28 50.11 57.05 51.42 80.64 47.95 60.94 49.95 46.24 62.24 60.63 50.62 51.21 62.68 59.32 58.24 51.21 35.06 53.74 49.30 50.11 41.44 51.42 28.74 47.95 55.72 49.95
Guan_HEU_task2_3 GuanHEU2024 44 55.300 52.43 66.58 50.95 53.34 50.58 58.08 52.74 51.30 49.32 83.60 55.05 52.22 55.95 66.92 52.05 41.16 53.95 32.42 48.47 62.71 53.94 50.95 71.16 50.58 61.28 52.74 66.92 49.32 46.80 55.05 68.52 55.95 55.32 52.05 78.34 53.95 77.76 48.47
Guan_HEU_task2_4 GuanHEU2024 43 55.569 53.07 67.64 51.05 54.58 50.42 61.40 53.42 51.84 49.32 84.22 55.63 51.30 56.11 66.82 51.95 41.64 53.32 32.74 48.53 62.73 55.22 51.05 70.62 50.42 63.28 53.42 67.18 49.32 46.98 55.63 68.06 56.11 53.52 51.95 77.12 53.32 77.58 48.53
Wang_iflytek_task2_1 Wangiflytek2024 11 61.088 68.89 60.16 51.37 71.32 60.16 83.24 61.05 69.06 54.53 78.96 53.21 73.68 53.26 79.10 51.21 51.46 50.16 65.82 50.79 62.58 50.44 51.37 57.58 60.16 74.44 61.05 60.96 54.53 69.76 53.21 68.72 53.26 65.26 51.21 61.02 50.16 61.80 50.79
Wang_iflytek_task2_2 Wangiflytek2024 18 59.713 65.83 60.16 51.37 49.76 49.89 83.24 61.05 69.06 54.53 78.96 53.21 73.68 53.26 79.10 51.21 51.46 50.16 65.82 50.79 62.28 50.44 51.37 55.38 49.89 74.44 61.05 60.96 54.53 69.76 53.21 68.72 53.26 65.26 51.21 61.02 50.16 61.80 50.79
Wang_iflytek_task2_3 Wangiflytek2024 20 59.559 66.37 60.16 51.37 71.32 60.16 83.24 61.05 69.06 54.53 78.96 53.21 53.94 48.26 79.10 51.21 51.46 50.16 65.82 50.79 60.71 50.44 51.37 57.58 60.16 74.44 61.05 60.96 54.53 69.76 53.21 52.66 48.26 65.26 51.21 61.02 50.16 61.80 50.79
Wang_iflytek_task2_4 Wangiflytek2024 31 58.250 63.52 60.16 51.37 49.76 49.89 83.24 61.05 69.06 54.53 78.96 53.21 53.94 48.26 79.10 51.21 51.46 50.16 65.82 50.79 60.43 50.44 51.37 55.38 49.89 74.44 61.05 60.96 54.53 69.76 53.21 52.66 48.26 65.26 51.21 61.02 50.16 61.80 50.79
Yang_IND_task2_1 YangIND2024 10 61.354 68.05 60.20 51.37 71.34 60.16 75.67 53.00 69.06 54.53 78.96 53.21 73.72 53.26 76.57 63.24 51.46 50.16 65.72 50.79 63.60 50.48 51.37 57.65 60.16 71.08 53.00 61.06 54.53 69.68 53.21 68.77 53.26 80.65 63.24 60.88 50.16 61.80 50.79
Yang_IND_task2_2 YangIND2024 16 59.969 65.07 60.20 51.37 49.81 49.89 75.67 53.00 69.06 54.53 78.96 53.21 73.72 53.26 76.57 63.24 51.46 50.16 65.72 50.79 63.30 50.48 51.37 55.46 49.89 71.08 53.00 61.06 54.53 69.68 53.21 68.77 53.26 80.65 63.24 60.88 50.16 61.80 50.79
Yang_IND_task2_3 YangIND2024 17 59.805 65.57 60.20 51.37 71.34 60.16 75.67 53.00 69.06 54.53 78.96 53.21 53.86 48.26 76.57 63.24 51.46 50.16 65.72 50.79 61.67 50.48 51.37 57.65 60.16 71.08 53.00 61.06 54.53 69.68 53.21 52.66 48.26 80.65 63.24 60.88 50.16 61.80 50.79
Yang_IND_task2_4 YangIND2024 29 58.489 62.80 60.20 51.37 49.81 49.89 75.67 53.00 69.06 54.53 78.96 53.21 53.86 48.26 76.57 63.24 51.46 50.16 65.72 50.79 61.38 50.48 51.37 55.46 49.89 71.08 53.00 61.06 54.53 69.68 53.21 52.66 48.26 80.65 63.24 60.88 50.16 61.80 50.79



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
41 DCASE2024_baseline_task2_MAHALA DCASE2024baseline2024 AE 267928 log-mel energies
39 DCASE2024_baseline_task2_MSE DCASE2024baseline2024 AE 267928 log-mel energies
62 Wilkinghoff_FKIE_task2_1 WilkinghoffFKIE2024 CNN, k-means, ensemble 127724380 FFT, STFT mixup, feature exchange average 10 high-pass filtering, zero-padding
67 Wilkinghoff_FKIE_task2_2 WilkinghoffFKIE2024 CNN, k-means, ensemble 127724380 FFT, STFT mixup, feature exchange average 10 high-pass filtering, zero-padding
69 Wilkinghoff_FKIE_task2_3 WilkinghoffFKIE2024 CNN, k-means, ensemble 127724380 FFT, STFT mixup, feature exchange average 10 high-pass filtering, zero-padding
26 Fujimura_NU_task2_1 FujimuraNU2024 CNN, k-means 518844040 spectrogram, spectrum mixup, cutmix, resize 97th percentile 90 external training data
35 Fujimura_NU_task2_2 FujimuraNU2024 CNN 160329360 spectrogram, spectrum mixup, cutmix 97th percentile 30 external training data
28 Fujimura_NU_task2_3 FujimuraNU2024 CNN, k-means 185835880 mel spectrogram, spectrum mixup,cutmix,resize 97th percentile external training data
27 Fujimura_NU_task2_4 FujimuraNU2024 CNN, k-means 177541480 spectrogram, spectrum mixup, cutmix, resize 97th percentile 30
9 Zhao_CUMT_task2_1 ZhaoCUMT2024 conditional AE log-mel energies
12 Zhao_CUMT_task2_2 ZhaoCUMT2024 conditional AE log-mel energies
15 Zhao_CUMT_task2_3 ZhaoCUMT2024 conditional AE log-mel energies
23 Zhao_CUMT_task2_4 ZhaoCUMT2024 conditional AE log-mel energies
19 Wang_USTC_task2_1 WangUSTC2024 AE log-mel spectrogram mixup average OpenL3 2 embeddings
30 Wang_USTC_task2_2 WangUSTC2024 AE log-mel spectrogram mixup average OpenL3 2 embeddings
32 Wang_USTC_task2_3 WangUSTC2024 AE log-mel spectrogram mixup average OpenL3 2 embeddings
36 Wang_USTC_task2_4 WangUSTC2024 AE log-mel spectrogram mixup average OpenL3 2 embeddings
75 Lee_KNU_task2_1 LeeKNU2024 source separation 1834833 STFT
79 Lee_KNU_task2_2 LeeKNU2024 source separation 1834833 STFT
73 Lee_KNU_task2_3 LeeKNU2024 source separation 1834833 STFT
77 Lee_KNU_task2_4 LeeKNU2024 source separation 1834833 STFT
14 Qian_NIVIC_task2_1 QianNIVIC2024 k-means log-mel energies, spectrogram mixup
22 Qian_NIVIC_task2_2 QianNIVIC2024 k-means log-mel energies, spectrogram mixup
25 Qian_NIVIC_task2_3 QianNIVIC2024 k-means log-mel energies, spectrogram mixup
34 Qian_NIVIC_task2_4 QianNIVIC2024 k-means log-mel energies, spectrogram mixup
81 Jiang_CUP_task2_1 JiangCUP2024 k-means, CNN, ensemble 59676914 spectrogram mixup maximum 10 pre-trained model
80 Jiang_CUP_task2_2 JiangCUP2024 k-means, CNN, ensemble 59676914 spectrogram mixup maximum 10 pre-trained model
84 Jiang_CUP_task2_3 JiangCUP2024 k-means, CNN, ensemble 59676914 spectrogram mixup maximum 10 pre-trained model
82 Jiang_CUP_task2_4 JiangCUP2024 k-means, CNN, ensemble 59676914 spectrogram mixup maximum 10 pre-trained model
4 Jiang_THUEE_task2_1 JiangTHUEE2024 pre-trained models, CNN, ensemble 360M spectrogram, raw waveform specaug median 4
6 Jiang_THUEE_task2_2 JiangTHUEE2024 pre-trained models, flow model, ensemble 360M spectrogram specaug median 4
7 Jiang_THUEE_task2_3 JiangTHUEE2024 pre-trained models, CNN, flow model, ensemble 360M spectrogram specaug median 5
8 Jiang_THUEE_task2_4 JiangTHUEE2024 pre-trained models, CNN, flow model, ensemble 360M spectrogram specaug median 5 classification
3 Lv_AITHU_task2_1 LvAITHU2024 pre-trained models, ensemble 360M spectrogram specaug median 3
5 Lv_AITHU_task2_2 LvAITHU2024 pre-trained models, ensemble 360M spectrogram specaug median 3
2 Lv_AITHU_task2_3 LvAITHU2024 pre-trained models, ensemble 700M spectrogram specaug median 7
1 Lv_AITHU_task2_4 LvAITHU2024 pre-trained models, ensemble 700M spectrogram specaug median 7
68 Yin_Midea_task2_1 YinMidea2024 CNN 3376606 spectrum
63 Yin_Midea_task2_2 YinMidea2024 CNN, k-means 3376606 spectrum
83 Yin_Midea_task2_3 YinMidea2024 CNN 3376606 spectrum mixup
70 Yin_Midea_task2_4 YinMidea2024 CNN 3376606 spectrum mixup, time warping, SMOTE
85 Perez_UPV_task2_1 PerezUPV2024 normalizing flow 236000 log-mel energies, CQT wide_resnet_50
61 Wu_IACAS_task2_1 WuIACAS2024 CNN, ensemble 28592295 STFT, raw waveform, spectrogram mixup average HuBert, BEATs, UniSpeech, WavLM, Wav2Vec
50 Wu_IACAS_task2_2 WuIACAS2024 CNN, ensemble 28592295 STFT, raw waveform, spectrogram mixup average HuBert, BEATs, UniSpeech, WavLM, Wav2Vec
47 Wu_IACAS_task2_3 WuIACAS2024 CNN, ensemble 28592295 STFT, raw waveform, spectrogram mixup average HuBert, BEATs, UniSpeech, WavLM, Wav2Vec
66 Wu_IACAS_task2_4 WuIACAS2024 CNN, ensemble 28592295 STFT, raw waveform, spectrogram mixup average HuBert, BEATs, UniSpeech, WavLM, Wav2Vec
58 Li_SMALLRICE_task2_1 LiSMALLRICE2024 Transformer 759830926 mel spectrogram time shift, mixup, manifold mixup average 7 pre-trained model
59 Li_SMALLRICE_task2_2 LiSMALLRICE2024 Transformer 576931952 mel spectrogram time shift, mixup, manifold mixup average 7 pre-trained model
53 Li_SMALLRICE_task2_3 LiSMALLRICE2024 Transformer 93282703 mel spectrogram time shift, mixup, manifold mixup pre-trained model
60 Li_SMALLRICE_task2_4 LiSMALLRICE2024 Transformer 750369166 mel spectrogram time shift, mixup, manifold mixup average 8 pre-trained model
46 Huang_Xju_task2_1 HuangXju2024 VAE 301712 log-mel energies
55 Huang_Xju_task2_2 HuangXju2024 VAE 301712 log-mel energies
88 Guo_BIT_task2_1 GuoBIT2024 Transformer 9679503 log-mel energies CED-Mini pre-trained model, embeddings
76 Guo_BIT_task2_2 GuoBIT2024 CNN, denoising diffusion probability model 35704705 log-mel energies
48 Guo_BIT_task2_3 GuoBIT2024 GMM 33000 log-mel energies SMOTE
86 Guo_BIT_task2_4 GuoBIT2024 Transformer, CNN, denoising diffusion probability model, GMM, ensemble 45417208 log-mel energies SMOTE weighted average CED-Mini 3 pre-trained model, embeddings
37 Wan_HFUU_task2_1 WanHFUU2024 self-supervised learning log-mel energies mixup
51 Wan_HFUU_task2_2 WanHFUU2024 self-supervised learning log-mel energies mixup
49 Wan_HFUU_task2_3 WanHFUU2024 self-supervised learning log-mel energies mixup
38 Wan_HFUU_task2_4 WanHFUU2024 self-supervised learning log-mel energies mixup
42 Kong_IMECAS_task2_1 KongIMECAS2024 Barlowtwins 541008 log-mel energies
40 Kong_IMECAS_task2_2 KongIMECAS2024 Barlowtwins 541008 log-mel energies
45 Kong_IMECAS_task2_3 KongIMECAS2024 Barlowtwins 541008 log-mel energies
52 Kong_IMECAS_task2_4 KongIMECAS2024 Barlowtwins 541008 log-mel energies
72 Hai_SCU_task2_1 HaiSCU2024 VAE, k-means, CNN 11722382 log-mel energies, fft mixup, SMOTE, statistics exchange, feature exchange
71 Kim_DAU_task2_1 KimDAU2024 AE, LTC 253207275 STFT multi-view
78 Bian_NR_task2_1 BianNR2024 AE,CNN 229249 spectrogram time stretching
74 Bian_NR_task2_2 BianNR2024 AE,CNN 262017 spectrogram time stretching
93 Gleichmann_TNT_task2_1 GleichmannTNT2024 CNN-VAE 627335 LPC multiple sampling none
96 Gleichmann_TNT_task2_2 GleichmannTNT2024 CNN-VAE 204000 LPC multiple sampling none
94 Gleichmann_TNT_task2_3 GleichmannTNT2024 CNN-VAE 447143 LPC multiple sampling none
95 Gleichmann_TNT_task2_4 GleichmannTNT2024 CNN-VAE 203153 LPC multiple sampling none
89 Kim_CAU_task2_1 KimCAU2024 CNN, k-means 180952716 spectrogram, raw waveform speed perturbation Wav2Vec2.0, AST pre-trained model
91 Kim_CAU_task2_2 KimCAU2024 CNN, k-means 180952716 spectrogram, raw waveform speed perturbation Wav2Vec2.0, AST pre-trained model
90 Kim_CAU_task2_3 KimCAU2024 CNN, k-means 180952716 spectrogram, raw waveform speed perturbation Wav2Vec2.0, AST pre-trained model
92 Kim_CAU_task2_4 KimCAU2024 CNN, k-means 180952716 spectrogram, raw waveform speed perturbation Wav2Vec2.0, AST pre-trained model
54 Zhang_HEU_task2_1 ZhangHEU2024 GMM 33024 log-mel energies
87 Zhang_HEU_task2_2 ZhangHEU2024 GMM 33024 log-mel energies SMOTE
64 Zhang_HEU_task2_3 ZhangHEU2024 GMM 33024 log-mel energies SMOTE
57 Zhang_HEU_task2_4 ZhangHEU2024 GMM 33024 log-mel energies SMOTE
13 Liu_CXL_task2_1 LiuCXL2024 k-means log-mel spectrogram mixup, time stretching, block mixing, pitch shifting average AST, SSAST, BATS 5
21 Liu_CXL_task2_2 LiuCXL2024 k-means log-mel spectrogram mixup, time stretching, block mixing, pitch shifting average AST, SSAST, BATS 5
24 Liu_CXL_task2_3 LiuCXL2024 k-means log-mel spectrogram mixup, time stretching, block mixing, pitch shifting average AST, SSAST, BATS 5
33 Liu_CXL_task2_4 LiuCXL2024 k-means log-mel spectrogram mixup, time stretching, block mixing, pitch shifting average AST, SSAST, BATS 5
65 Guan_HEU_task2_1 GuanHEU2024 CNN, k-means 12337152 log-mel energies
56 Guan_HEU_task2_2 GuanHEU2024 CNN, k-means 12337152 log-mel energies
44 Guan_HEU_task2_3 GuanHEU2024 CNN, k-means 11307772 log-mel energies
43 Guan_HEU_task2_4 GuanHEU2024 CNN, k-means 23644924 log-mel energies 2
11 Wang_iflytek_task2_1 Wangiflytek2024 AE log-mel spectrogram mixup average 2
18 Wang_iflytek_task2_2 Wangiflytek2024 AE log-mel spectrogram mixup average 2
20 Wang_iflytek_task2_3 Wangiflytek2024 AE log-mel spectrogram mixup average 2
31 Wang_iflytek_task2_4 Wangiflytek2024 AE log-mel spectrogram mixup average 2
10 Yang_IND_task2_1 YangIND2024 VAE, k-means MFCC mixup
16 Yang_IND_task2_2 YangIND2024 VAE, k-means MFCC mixup
17 Yang_IND_task2_3 YangIND2024 VAE, k-means MFCC mixup
29 Yang_IND_task2_4 YangIND2024 VAE, k-means MFCC mixup



Technical reports

FIRST-SHOT UNSUPERVISED ANOMALOUS SOUND DETECTION BASED ON CONVOLUTIONAL AUTOENCODER

Yuren Bian, Jun Li, Jiayun Chen
Industrial AI Research and Development Group, New Rise Digital Technology Co., Ltd., Hangzhou, China and New Rise Digital Technology Co., Ltd., Hangzhou, China

Abstract

This technical report outlines our team's submission to DCASE 2024 Task 2. A novel challenge introduced by this year's DCASE is the concealment of attribute information, such as machine operation conditions, for several types of machines. This approach more closely emulates real-world factory settings. We propose an anomaly detection model based on a memory-augmented convolutional autoencoder that directly operates on spectrograms without attribute information. Experimental results demonstrate that our method outperforms the baseline model for certain types of machines.

System characteristics
Classifier AE, CNN
System complexity 229249, 262017
Acoustic features spectrogram
Data augmentation time stretching
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

The NU systems for DCASE 2024 Challenge Task 2

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

Abstract

In this report, we present our developed anomalous sound detection (ASD) systems for DCASE 2024 Challenge Task 2. We propose three methods to improve ASD systems based on a discriminative approach. First, we enhance a discriminative feature extractor by using multi-resolution spectrograms as input and implementing new training strategy and data augmentation for its training. Second, we generate pseudo-attribute labels to effectively train the discriminative feature extractor even for some machines without any attribute labels, where the pseudo-attribute labels are obtained by self-supervised learning using artificially processed data as negative samples. Third, we utilize Audioset as an external training dataset to further improve ASD performance, where we carefully extract useful samples from it using a pre-trained feature extractor. Our developed ensemble system has achieved 67.26% 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, k-means
System complexity 160329360, 177541480, 185835880, 518844040
Acoustic features mel spectrogram, spectrogram, spectrum
Data augmentation mixup, cutmix, mixup, cutmix, resize, mixup,cutmix,resize
Decision making 97th percentile
Subsystem count 30, 90
External data usage external training data
PDF

Anomaly Sound Detector Based on Variational Autoencoder with Hyperparameter Optimization Strategy

Lars C. Gleichmann, Yeremia G. Adhisantoso, Alexander Lange, Quy Le Xuan
Predictive Maintenance, Institute for Information Processing (TNT), Hanover, Germany and Institute for Information Processing (TNT), Hanover, Germany and Structural Health Monitoring, Institute for Information Processing (TNT), Hanover, Germany

Abstract

The second task of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2024 challenge addresses the difficulties of domain adaptation and generalization in Anomalous Sound Detection (ASD). We present two types of Variational Autoencoders (VAEs) to overcome these challenges. Linear prediction coefficients provide a sparse and meaningful representation of the original raw audio clips for our models. This report also introduces two optimization strategies for setting reasonable hyperparameters for anomalous sound detectors.

System characteristics
Classifier CNN-VAE
System complexity 203153, 204000, 447143, 627335
Acoustic features LPC
Data augmentation Multiple sampling
External data usage none
PDF

Self-supervised Anomalous Sound Detection with Statistical Clustering and Contrastive Learning

Jiantong Tian, Hejing Zhang, Shiheng Zhang, Feiyang Xiao, Qiaoxi Zhu, Wenwu Wang, Jian Guan
Group of Intelligent Signal Processing, College of Computer Science and Technology, Harbin Engineering University, Harbin, China and University of Technology Sydney, Ultimo, Australia and Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK

Abstract

This report describes our submission for DCASE 2024 Challenge Task 2. The task aims for first-shot anomalous sound detection and further restricts the use of attribute information (metadata) accompanied by audio signals. This requires the anomaly detection system to function correctly for machine types with and without attribute information. We introduce a statistical clustering strategy to obtain statistical information on audio signals as pseudo-labels to address this issue. In addition, we propose a contrastive learning strategy to enhance audio feature representation by using statistical information, further improving anomaly detection performance. Experiments demonstrate the effectiveness of our proposed strategies, and the results show that all our systems outperform the baseline methods, enabling the model to adapt to the first-shot scenarios without attribute information. Our best system can achieve 71.4% in the harmonic mean of AUC in the source domain, 63.6% in AUC in the target domain, and 56.6% in pAUC.

System characteristics
Classifier CNN, k-means
System complexity 11307772, 12337152, 23644924
Acoustic features log-mel energies
Subsystem count 2
PDF

Anomalous Sound Detection Based on Unsupervised Learning and Ensemble Method

Kai Guo, Fengrun Zhang
School of Information and Electronics, Beijing Institute of Technology, Beijing, China

Abstract

Over the past few years, self-supervised methods have significantly advanced the field of Anomalous sound detection. However, the real-world application of these methods is often hampered by the lack of available prior knowledge and auxiliary labels, which restricts the models’ ability to generalize. In the DCASE 2024 Challenge Task 2, attribute information for several machine types is absent from both the development and evaluation datasets, reflecting the realities of practical scenarios. To solve the above problems, we design two unsupervised machine anomalous sound detection models and an ensemble system that achieves better performance than the baseline model.

System characteristics
Classifier CNN, Denoising Diffusion Probability Model, GMM, Transformer, ensemble
System complexity 33000, 35704705, 45417208, 9679503
Acoustic features log-mel energies
Data augmentation SMOTE
Decision making weighted average
System embeddings CED-Mini
Subsystem count 3
External data usage pre-trained model, embeddings
PDF

ANOMALOUS SOUND DETECTION BY SELF-SUPERVISED LEARNING OF Variational Auto-Encoder WITH DOMAIN SHIFT TECHNIQUES

Jianghan Hai, Dengjian Zhou, Ruihang Liu, Yue Ivan Wu
School of Software Engineering, Sichuan Uninversity., Chengdu, China and School of Computer Science, Sichuan Uninversity., Chengdu, China and School of Electronics and Information Engineering, Sichuan Uninversity., Chengdu, China

Abstract

In this paper, we introduce an advanced abnormal sound detection (ASD) system that integrates two innovative approaches to improve detection performance. Firstly, we utilize a self-supervised learning method known as Feature Exchange (FeatEx) to map raw data to meta data and obtain robust feature embeddings for enhanced discrimination of non-target sound events. Secondly, we expand a serial approach by employing an outlier-exposed feature extractor and an anomaly detector based on ResNet18 inlier modeling. The model undertake end-to-end joint optimization utilizing a variational autoencoder (VAE) feature extractor based on the intermediate inner-layer model vectors. Additionally, domain generalization techniques such as domain-invariant latent space modeling in normalized and hybrid streams are introduced to address the domain drift problem by resolving ”transfer entanglement”. To further enhance performance, our data is augmented using Mixup and Smote methods respectively. Furthermore, our system employs an ensemble learning strategy that combines anomaly scores calculated directly through normalization process with earlier models trained using optimized feature embeddings. Ultimately, our system achieves state-of-the-art performance on the DCASE 2024 ASD dataset for two machine types through weighted anomaly scores on the development set. Through the integration of self-supervised learning and domain generalization techniques, our ASD system not only reduces reliance on manual annotation but also enhances adaptability and robustness across different sound environments. This research outcome offers a novel perspective and solution for abnormal sound detection field.

System characteristics
Classifier CNN, VAE, k-means
System complexity 11722382
Acoustic features fft, log-mel energies
Data augmentation mixup, SMOTE, statistics exchange, feature exchange
PDF

Unsupervised Anomaly Sound Detection Based on GammaVAE

Shun Huang, Yunxiang Zhang
School of Computer Science and Technology, Xinjiang University, Urumqi, Xinjiang, China

Abstract

This technical report describes the submission to Task 2 of the DCASE 2024 challenge. Assuming the data follows a Gamma distribution, we employed a Gamma Variational Autoencoder (GammaVAE) for modeling, and utilized Mean Squared Error (MSE) scores and Mahalanobis distance for evaluation. Experimental results revealed that our system outperformed the baseline in the target domain on certain machines.

System characteristics
Classifier VAE
System complexity 301712
Acoustic features log-mel energies
PDF

ANOMALOUS SOUND DETECTION BASED ON PSEUDO LABELS FROM GUIDED CLUSTERING

Yaocong Wang, Xinlong Deng, Jie Jiang, Qiuqiang Kong
China University of Petroleum (Beijing), Beijing, China and The Chinese University of Hong Kong, HongKong, China

Abstract

This technical report presents a description of the CUP submission for Task 2 “first-shot unsupervised anomalous sound detection for machine condition monitoring” of the DCASE 2024 Challenge. The submitted system is an adaptation of a previously proposed model which utilizes static and dynamic frequency information and is trained through an auxiliary classification task with sub-cluster AdaCos loss. In this work, we focus on the clustering of machine sound clips under attribute-unavailable conditions such that attribute classification based methods can be extended to machine sound clips without attribute information for detecting anomalous sounds.

System characteristics
Classifier CNN, ensemble, k-means
System complexity 59676914
Acoustic features spectrogram
Data augmentation mixup
Decision making maximum
Subsystem count 10
External data usage pre-trained model
PDF

THUEE System for First-Shot Unsupervised Anomalous Sound Detection

Anbai Jiang, Xinhu Zheng, Yihong Qiu, Weijia Zhang, Boyuan Chen, Pingyi Fan, Wei-Qiang Zhang, Cheng Lu, Jia Liu
Department of Electronic Engineering, Tsinghua University, Beijing, China and Schools of Economy, North China Electric Power University, Beijing, China and Xingjian College, Tsinghua University, Beijing, China

Abstract

This report presents our work for DCASE 2024 Task 2: first shot unsupervised anomalous sound detection for machine condition monitoring. This year’s challenge is heightened by the introduction of additional machine types and the absence of training labels. To solve these problems, multiple pre-trained models are employed in the submission, along with a Dual Branch CNN model and a flow model. The pre-trained models are fine-tuned with Low-Rank Adaptation (LoRA). Finally, by fusing the systems above, we achieve the best hmean of 68.38% on the development set.

System characteristics
Classifier CNN, Pre-trained models, ensemble, flow model
System complexity 360M
Acoustic features raw waveform, spectrogram
Data augmentation specaug
Decision making median
Subsystem count 4, 5
External data usage classification
PDF

Colligate embeddings from pretrained models based on different preprocessing methods

Hyun Jun Kim, Hyeon Gyu Bae, Min Jun Kim, Yun Seo Lee, Changwon Lim, Jaeheon Lee
Chung Ang University, Seoul, Korea

Abstract

DCASE 2024 challenge Task2 is about first-shot unsupervised anomalous sound detection. To solve this problem, we employed self-supervised learning with various methods to enable the model to achieve general and robust performance on diverse machine sounds with limited information. The methods include combining embeddings from pre-trained models based on different audio representations, attentive statistics pooling, and a memory bank. By applying these methods, we successfully achieved a higher score on development dataset compared to the baseline.

System characteristics
Classifier CNN, k-means
System complexity 180952716
Acoustic features raw waveform, spectrogram
Data augmentation Speed perturbation
System embeddings Wav2Vec2.0, AST
External data usage pre-trained model
PDF

Unsupervised Multi-View Reconstruction Autoencoder and Liquid Time Constant Model-Based First-Shot Anomaly Detection For Machine Condition Monitoring

JeongSik Kim, YoungHoon Jo, DongMin Lee, Ji Heon Kim, GeonYong Jeong, Jeongil Seo, Suk-Hwan Lee
Department of Computer Engineering, Dong-A, University, South Korea, Busan

Abstract

This technical report presents our approach for DCASE 2024 Task 2: first-shot unsupervised anomalous sound detection for machine condition monitoring. In this year task 2 focuses on first-shot challenge and also introduces real-world application that provides no additional information for some machine type. In order to tackle this challenges we have developed multi-view reconstruction based system to detect first-shot anomalous sounds more accurately and also without any additional attribute information. Our proposed system has been evaluated using DCASE 2024 Task 2 Development Dataset, and from the result we have achieved an average area under the curve detection result of 74.59%.

System characteristics
Classifier AE, LTC
System complexity 253207275
Acoustic features STFT
Front end system Multi-View
PDF

Anomalous Sound Detection System Based on Similar-Pairs Contrastive Learning

Kong Dewei, Yu Hongjiang, Wang Shuai, Zhang Bo
Beijing, China

Abstract

This technical report presents our approach for Task 2 of the DCASE 2024 challenge, which focuses on unsupervised anomalous sound detection for machine condition monitoring. We constructed four subsystems based on similar-pairs contrastive learning, where the fisrt two are based on SMOTE, the third and the fourth subsystem are based on two augmentation method to get more generalizations. The difference between the first and second subsystem is which method is used to calculate the anomaly score, MSE or MAHALA. The same is true for the difference between the third and fourth systems.

System characteristics
Classifier Barlowtwins
System complexity 541008
Acoustic features log-mel energies
PDF

Anomalous sound detection system with source separation model-based feature extractor

Seunghyeon Shin, Seokjin Lee
School of Electronic and Electrical Engineering, Kyungpook National University, Daegu, Republic of Korea

Abstract

This technical report presents an anomalous detection system developed for DCASE 2024 Task 2. Our proposed system employs a neural network to extract relevant features and calculates anomaly scores using the Mahalanobis distance with a covariance estimator. Notably, our system does not rely on any attribute information from the machines, and only minor hyperparameter adjustments are required, regardless of the machine class. These characteristics align well with the intended objectives of the task. Our approach leverages signals from machines other than the training target and trains the neural network to separate these other signals. Consequently, we can train complex neural network models effectively, even with a limited number of samples. As a result, our method achieved similar result compared to the DCASE 2024 Task 2 baseline model despite the insufficient training.

System characteristics
Classifier Source separation
System complexity 1834833
Acoustic features STFT
PDF

The SMALL RICE Submission for the DCASE 2024 Task 2: Anomalous Sound Detection Using Sub-Cluster Noisy-Arcmix

Chenyu Liu, Gang Li, Junbo Zhang, Jizhong Liu, Heinrich Dinkel, Yongqing Wang, Zhiyong Yan, Yujun Wang, Bin Wang
AI Lab, Xiaomi Corporation, China

Abstract

This paper describes our submission for the DCASE 2024 task 2. The objective is identifying whether the sound emitted from a machine is normal or anomalous without having access to anomalous samples. The ASD model we designed to calculate the anomaly scores is a CED based supervised model. To alleviate the problem of domain shifts, we use sub-cluster noisy-arcmix combined with asymmetric focal loss to balance the data weights while learn more compact intra-class representations for normal samples. In addition, we explore data augmentation methods such as manifold mixup and FeatEx to further improve the model perfomance. Our best single model achieves a pAUC of 55.81%, a source domain AUC of 67.79%, and a target domain AUC of 65.88% on the development dataset.

System characteristics
Classifier Transformer
System complexity 576931952, 750369166, 759830926, 93282703
Acoustic features mel spectrogram
Data augmentation time shift, mixup, manifold mixup
Decision making average
Subsystem count 7, 8
External data usage pre-trained model
PDF

DUAL-MODE FRAMEWORK FOR FIRST-SHOT UNSUPERVISED ANOMALOUS SOUND DETECTION IN MACHINE CONDITION MONITORING

Yihao Liu
ChaoXiLi, Hangzhou, China

Abstract

This technical report presents our solution for the DCASE 2024 Challenge Task 2, which targets First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring. This year’s task requires the development of a system that functions effectively both with and without attribute information, reflecting real-world scenarios where such data may not always be available. To address this challenge, we propose a dual-mode anomaly detection framework that adapts seamlessly to the availability of attribute information. Our approach leverages advanced pre-training techniques, sophisticated embedding extraction, and refined inlier modeling. In scenarios where attribute information is available, it enhances detection performance; when it is not, the system employs a robust, self-contained strategy to maintain high performance. Our dual-mode system achieves a harmonic mean of 61.598% across all machine types and domains for both the AUC and pAUC (p = 0.1) on the development set, demonstrating significant improvement and ensuring versatility under varying data conditions.

System characteristics
Classifier k-means
Acoustic features log-mel spectrogram
Data augmentation mixup, time stretching, block mixing, pitch shifting
Decision making average
System embeddings AST, SSAST, BATS
Subsystem count 5
PDF

AITHU System for First-Shot Unsupervised Anomalous Sound Detection

Zhiqiang Lv, Anbai Jiang, Bing Han, Yuzhe Liang, Yanmin Qian, Xie Chen, Jia Liu, Pingyi Fan
Algorithm Group, Huakong AI Plus Company Limited, Beijing, China and Department of Electronic Engineering, Tsinghua University, Beijing, China and Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China

Abstract

Unsupervised pre-trained models have demonstrated significant promise in anomaly detection with domain shifts. The DCASE 2024 Challenge Task 2 focuses on first-shot unsupervised anomalous sound detection. Compared with last year, this year’s challenge omit the attributes for some machine types. To solve this, we leverage large pre-trained models to generate robust representations for the audio. Novel usage of pseudo labeling and Low-Rank Adaptation (LoRA) are explored in the work. Additionally, we introduce SMOTE for domain equalization. Through the fusion of various models and methods, we have achieved a hmean of 68.02% on the development dataset.

System characteristics
Classifier Pre-trained models, ensemble
System complexity 360M, 700M
Acoustic features spectrogram
Data augmentation specaug
Decision making median
Subsystem count 3, 7
PDF

ANOMALOUS SOUND DETECTION IN INDUSTRIAL MACHINERY USING NORMALIZING FLOW-BASED DEEP LEARNING

Natalia Pérez García de la Puente, Francisco Pastor Naranjo, Miguel López-Pérez, Gema Piñero, Valery Naranjo
HumanTech, Universitat Politècnica de València, Spain, Valencia, Spain and ITEAM, Universitat Polit`ecnica de València, Spain, Valencia, Spain

Abstract

This technical report describes our approach for Task 2 of the DCASE 2024 Challenge. This task aims to develop an anomalous sound detection (ASD) system to determine whether the sound emitted from a target machine is normal or anomalous. To tackle this task, we propose an unsupervised deep learning model based on a normalizing flow architecture. Our framework consists of a pre-trained encoder (WideResNet50) and a multi-scale generative decoder to estimate the log-likelihoods of feature vectors. The input to the model is an image comprising four different time-frequency representations of the sounds (Mel spectrogram, CQT-chroma, tonnetz, and spectral contrast) together with five 1D characteristics computed along the time index. All the 2D and 1D features are concatenated in the frequency dimension, resulting in an image 158 pixels high, with their width depending on the duration of the sounds.

System characteristics
Classifier normalizing flow
System complexity 236000
Acoustic features CQT, log-mel energies
System embeddings wide_resnet_50
PDF

Unified Anomaly Detection for Machine Condition Monitoring: Handling Attribute-Rich and Attribute-Free Scenarios

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

Abstract

In this report, we present our solution to the DCASE 2024 Challenge Task 2, focusing on First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring. The challenge this year involves handling machine types with varying levels of attribute and domain information. Our approach addresses this by categorizing the machines into two groups: those with attribute labels and those without. We respectively train two models that perform attribute classification for these two groups, both based on a pretrained model that performs domain classification. Our system achieves 62.001% in the harmonic mean of AUC and pAUC (p = 0.1) across all machine types and domains on the development set.

System characteristics
Classifier k-means
Acoustic features log-mel energies, spectrogram
Data augmentation mixup
PDF

TWO-STEP ANOMALY DETECTION: INTEGRATING ATTRIBUTE CLASSIFICATION AND GENERATIVE MODELING WITH ATTRIBUTE INFERENCE FOR DIVERSE MACHINE TYPES

Lei Wang, Mingqi Cai, Jia Pan, Tian Gao, Xin Fang
iFLYTEK, Hefei, China

Abstract

This study presents a novel approach to address the DCASE2024 Challenge Task2[1], 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. Our proposed method combines attribute classification and generative modeling to address the variability in attribute information across different machine types. Initially, we perform attribute prediction or clustering to infer labels for machines without explicit attribute information. Using these inferred labels, we then apply comprehensive attribute classification across all machine types. Concurrently, we integrate an Autoencoder (AE) to analyze reconstruction losses, enhancing anomaly detection. This two-step approach – first predicting or clustering attributes, and then merging attribute classification with generative model results – ensures robust and effective anomaly detection, maintaining high performance regardless of the presence or absence of attribute information across various scenarios. Experimental results demonstrate the effectiveness of our approach, achieving a competitive harmonic mean of AUC and PAUC(p = 0.1) of 63.09% on the development set. This innovative framework offers a versatile solution for anomaly detection in machine condition monitoring, accommodating real-world data variability and enhancing overall system robustness.

System characteristics
Classifier AE
Acoustic features log-mel spectrogram
Data augmentation mixup
Decision making average
Subsystem count 2
PDF

Hybrid Anomaly Detection Approach for DCASE 2024 Task 2

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

Abstract

Addressing the unique challenge of the DCASE 2024 Task 2, where the availability of attribute information varies, we propose a hybrid anomaly detection approach that combines generative and discriminative techniques. Leveraging both autoencoder (AE) for unsupervised learning and attribute classification for supervised learning, our system is designed to perform effectively under diverse conditions. The AE is trained to reconstruct normal sound data and detect anomalies, providing robustness in scenarios where attribute information is unavailable. Simultaneously, the attribute classification component enhances detection performance when attribute information is present. By seamlessly integrating these approaches, our system achieves a balanced performance across different conditions, ensuring reliable anomaly detection in machine condition monitoring applications.

System characteristics
Classifier AE
Acoustic features log-mel spectrogram
Data augmentation mixup
Decision making average
System embeddings OpenL3
Subsystem count 2
External data usage embeddings
PDF

Abnormal Sound Detection Based on Domain Generalization

Mengyuan Wan, Yong Sun, Junjie Wang, Jiajun Wang, Shengbing Chen, Mengyuan Liu
Research and Development Group, Hefei University, Hefei, China and Hefei University, Hefei, China

Abstract

This technical report describes the abnormal sound detection system we submitted for DCASE 2024 Task 2. Compared to previous challenges, this task not only focuses on the first shot issue in 2023, but also requires the system to run well when attribute information is available and unavailable. We submit four methods for machine state anomaly sound detection. The first and second methods are based on self-supervised learning, using the feature vector extracted from the convolutional neural network, using the outlier detection algorithm to identify abnormal sounds. The third method uses the mixup method for probability mixing, and the fourth method uses the combination of SMOTE and mixup. Experiments on the development set show that the performance of the four methods is better than that of the baseline model.

System characteristics
Classifier Self-supervised learning
Acoustic features log-mel energies
Data augmentation mixup
PDF

FKIE-VUB System for DCASE2024 Challenge Task 2: First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring

Kevin Wilkinghoff, Yacine Bel-Hadj
Fraunhofer FKIE, Wachtberg, Germany and Vrije Universiteit Brussel, Brussels, Belgium

Abstract

This report contains a description of the FKIE-VUB system submitted to task 2 “First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring” of the DCASE2024 Challenge. The submitted system is an adaptation of a previously proposed system based on an embedding model trained with an auxiliary classification task, which is imposed by self-supervised learning and provided meta information. The main modifications of the presented system are to replace the sub-cluster AdaCos loss with the AdaProj loss and to use balanced sample weights when training the embedding model. In experimental evaluations, it is shown that both modifications improve the resulting performance and that the proposed system significantly outperforms both baseline systems of the challenge as well as the model it is based on.

System characteristics
Classifier CNN, ensemble, k-means
System complexity 127724380
Acoustic features FFT, STFT
Data augmentation mixup, feature exchange
Decision making average
Subsystem count 10
Front end system high-pass filtering, zero-padding
PDF

Anomalous Sound Detection with Three-SubNetworks and Pre-Trained Models

Ting Wu, Jian Wen, Zhaoli Yan, Xiaobin Cheng
Key Laboratory of Noise and Vibration Research, 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

Abstract

Unsupervised pretrained models have been used successfully in a wide range of scenarios. This report presents our work for DCASE 2024 Task 2: First-shot unsupervised anomalous sound detection for machine condition monitoring. To solve this problem, a three-subnetworks is designed specifically for outlier exposure. The sample information is fully exploited to extract its embedding using classification networks as an auxiliary task, and then anomaly scores are calculated using clustering. Several pre-trained large models are fine-tuned with datasets from the DCASE 2024 challenge Task2 to further improve the performance. The ensemble of the above methods achieves an official score of 65.56% on the development dataset, being significantly superior to the baseline model’s performance.

System characteristics
Classifier CNN, ensemble
System complexity 28592295
Acoustic features STFT, raw waveform, spectrogram
Data augmentation mixup
Decision making average
System embeddings HuBert, BEATs, UniSpeech, WavLM, Wav2Vec
PDF

ADAPTIVE FRAMEWORK FOR FIRST-SHOT UNSUPERVISED ANOMALOUS SOUND DETECTION IN INDUSTRIAL MACHINE MONITORING

Jie Yang
Independent, Shanghai, China

Abstract

This technical report details our approach to addressing Task 2 of the DCASE 2024 Challenge, which centers on First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring. The objective of this year’s challenge is to create a system that functions efficiently regardless of the presence of attribute information, mirroring real-world situations where such data may be intermittently accessible. To tackle this challenge, we propose an adaptive anomaly detection framework that adjusts seamlessly to the availability of attribute information. Our method employs an attribute classification scheme for detecting anomalous sounds. In cases where attribute information is present, we perform detailed anomaly detection by subdividing all attributes. For situations lacking attribute information, we utilize domain-specific information for effective detection. The adaptive system achieved a harmonic mean of 57.75% across all machine types and domains for both AUC and pAUC (p= 0.1) on the development set. This result demonstrates significant improvement and ensures the system’s adaptability under varying data conditions. Moreover, the framework’s flexibility in handling different types of input data enhances its applicability in real-world industrial machine monitoring scenarios.

System characteristics
Classifier VAE, k-means
Acoustic features MFCC
Data augmentation mixup
PDF

FIRST-SHOT UNSUPERVISED ANOMALOUS SOUND DETECTION BASED ON SELF-SUPERVISED LEARNING

Jiawei Yin, Yu Gao, Wenbin Zhang
AI Innovation Center, Midea Group., Shanghai, China and Midea Group, Shanghai, China

Abstract

This technical report contains a description of Midea’s submission to Task 2 “First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring” of DCASE Challenge 2024. Compared with previous challenges, this task focuses on the first-shot problem, and some attribute information is unavailable, which brings many challenges. Our proposed system is based on a self-supervised learning approach by using a convolutional neural network to extract feature vectors from input sounds and an anomaly detection algorithm to detect abnormal sounds. The proposed method is evaluated using the DCASE 2024 Task 2 development dataset. The results show that the proposed method can effectively extract the sound features and significantly outperforms the baseline in detection performance.

System characteristics
Classifier CNN, k-means
System complexity 3376606
Acoustic features spectrum
Data augmentation mixup, mixup, time warping, SMOTE
PDF

LIGHTWEIGHT SOLUTION USING STATISTICAL ESTIMATION FOR FIRST-SHOT ANOMALOUS SOUND DETECTION

Shiheng Zhang, Hejing Zhang, Feiyang Xiao, Qiaoxi Zhu, Wenwu Wang, Jian Guan
Group of Intelligent Signal Processing, College of Computer Science and Technology, Harbin Engineering University, Harbin, China and University of Technology Sydney, Ultimo, Australia and Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK

Abstract

This report presents our submission for Task 2 of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2024 Challenge [1]. We introduce statistical strategies to build our lightweight non-deep learning anomalous sound detection (ASD) systems. We analyse the intrinsic statistical characteristics of machine sounds in the time-frequency domain. Then, different statistical information forms weights assigned to the frequency components or the time bins for frequency-weighted or time-weighted audio feature representation, resulting in frequency-weighted and time-weighted ASD systems, respectively. Additionally, the time-weighted system applies SMOTE for data augmentation to mitigate domain shift, which forms an SMOTE time-frequency-weighted ASD system. Finally, we use these systems to build an ensembled ASD system. Experiments show that all four systems achieve better performance than the baseline systems.

System characteristics
Classifier GMM
System complexity 33024
Acoustic features log-mel energies
Data augmentation SMOTE
PDF

ENHANCED UNSUPERVISED ANOMALOUS SOUND DETECTION USING CONDITIONAL AUTOENCODER FOR MACHINE CONDITION MONITORING

Ronghuan Zhao, Kelong Ren, Liang Zou
China University of Mining and Technology, Xuzhou, China

Abstract

This report outlines our approach to first-shot unsupervised anomalous sound detection for machine condition monitoring, developed for the DCASE 2024 Challenge Task 2. Given the constraint of only having normal operational data, our method focuses on leveraging generative models for anomaly detection by employing an Autoencoder (AE). Key components of our approach include training an AE model on normal sound data to use reconstruction loss for detecting anomalies, transforming sounds into log-mel spectrograms for better feature representation, incorporating attribute or domain labels in a conditional AE to enhance context-specific anomaly detection, normalizing reconstruction losses by domain to address machine variations, and inferring domain categories using classification or clustering when labels are absent. To further improve detection performance, we employ guided diffusion model for data augmentation, enhancing the diversity and robustness of the training data. We also implement custom filtering techniques tailored to sound signals, improving the quality and relevance of the input data. By integrating these advanced techniques, our approach significantly enhances the accuracy and reliability of anomaly detection, providing a robust tool for machine condition monitoring. Our approach achieved notable performance on the development set, demonstrating its effectiveness. The AUC for the target domain was 61.50% and for the source domain was 60.25%. Additionally, the Partial AUC values (p = 0.1) for the target and source domain was 53.26%. These results underscore the robustness and applicability of our methodology in detecting anomalous sounds in various operational contexts.

System characteristics
Classifier Conditional AE
Acoustic features log-mel energies
PDF