RIAD

Reported on 5 benchmarks across 1 task

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

Methodology5 results

Anomaly DetectiononAeBAD-V
Detection AUROC
56.1
best: 78.2 (MMR)
Anomaly DetectiononAeBAD-S
Detection AUROC
40
best: 87.1 (MSFR)
Anomaly DetectiononAeBAD-S
Segmentation AUPRO
58.2
best: 90.4 (MSFR)
Anomaly DetectiononMVTec AD
Detection AUROC
91.7
best: 99.9 (GLASS)
Anomaly DetectiononMVTec AD
Segmentation AUROC
94.2
best: 99.7 (WeakREST-Block)