SLSG

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
Detection AUROC (only logical)· 2023-04-30
89.6
best: 98.1 (PSAD)
SOTA
SLSG: Industrial Image Anomaly Detection by Learning Better Feature Embeddings and One-Class Classification arXiv:2305.00398
Anomaly DetectiononMVTec LOCO AD
Avg. Detection AUROC· 2023-04-30
90.3
best: 95.3 (CSAD)
SLSG: Industrial Image Anomaly Detection by Learning Better Feature Embeddings and One-Class Classification arXiv:2305.00398
Anomaly DetectiononMVTec LOCO AD
Detection AUROC (only structural)· 2023-04-30
91.4
best: 95.9 (PUAD-M)
SLSG: Industrial Image Anomaly Detection by Learning Better Feature Embeddings and One-Class Classification arXiv:2305.00398
Anomaly DetectiononMVTec LOCO AD
Segmentation AU-sPRO (until FPR 5%)· 2023-04-30
67.3
best: 83.2 (SAM-LAD)
SLSG: Industrial Image Anomaly Detection by Learning Better Feature Embeddings and One-Class Classification arXiv:2305.00398