GLCF

Reported on 4 benchmarks across 1 task · 1 paper · 1 SOTA

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

Methodology4 results

Anomaly DetectiononMVTec LOCO AD
Segmentation AU-sPRO (until FPR 5%)· 2023-03-10
70.3
best: 83.2 (SAM-LAD)
SOTA
Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection arXiv:2303.05768
Anomaly DetectiononMVTec LOCO AD
Avg. Detection AUROC· 2023-03-10
83.1
best: 95.3 (CSAD)
Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection arXiv:2303.05768
Anomaly DetectiononMVTec LOCO AD
Detection AUROC (only logical)· 2023-03-10
82.4
best: 98.1 (PSAD)
Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection arXiv:2303.05768
Anomaly DetectiononMVTec LOCO AD
Detection AUROC (only structural)· 2023-03-10
83.8
best: 95.9 (PUAD-M)
Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection arXiv:2303.05768