PFM

Reported on 3 benchmarks across 1 task

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

Methodology3 results

Anomaly DetectiononMVTec AD
Detection AUROC· uses extra data
97.5
best: 99.9 (GLASS)
Anomaly DetectiononMVTec AD
Segmentation AUPRO· uses extra data
93
best: 98.4 (WeakREST-Block)
Anomaly DetectiononMVTec AD
Segmentation AUROC· uses extra data
97.3
best: 99.7 (WeakREST-Block)