ComAD+DRAEM

Reported on 3 benchmarks across 1 task · 1 paper

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

Methodology3 results

Anomaly DetectiononMVTec LOCO AD
Avg. Detection AUROC· 2023-05-15
87.9
best: 95.3 (CSAD)
Component-aware anomaly detection framework for adjustable and logical industrial visual inspection arXiv:2305.08509
Anomaly DetectiononMVTec LOCO AD
Detection AUROC (only logical)· 2023-05-15
85.9
best: 98.1 (PSAD)
Component-aware anomaly detection framework for adjustable and logical industrial visual inspection arXiv:2305.08509
Anomaly DetectiononMVTec LOCO AD
Detection AUROC (only structural)· 2023-05-15
89.9
best: 95.9 (PUAD-M)
Component-aware anomaly detection framework for adjustable and logical industrial visual inspection arXiv:2305.08509