AD-CLSCNFs

Reported on 8 benchmarks across 1 task

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology8 results

Anomaly DetectiononBTAD
Detection AUROC
95.93
best: 98.3 (CPR)
Anomaly DetectiononBTAD
Segmentation AP
55.86
best: 84.6 (WeakREST-Block)
Anomaly DetectiononBTAD
Segmentation AUPRO
72.77
best: 97.5 (ReConPatch WRN-50)
Anomaly DetectiononBTAD
Segmentation AUROC
97.13
best: 99.3 (WeakREST-Block)
Anomaly DetectiononMVTec AD
Detection AUROC
98.85
best: 99.9 (GLASS)
Anomaly DetectiononMVTec AD
Segmentation AP
74.32
best: 87.6 (WeakREST-Block)
Anomaly DetectiononMVTec AD
Segmentation AUPRO
96.01
best: 98.4 (WeakREST-Block)
Anomaly DetectiononMVTec AD
Segmentation AUROC
98.74
best: 99.7 (WeakREST-Block)