INP-Fomer ViT-L (model-unified multi-class)

Reported on 4 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.

Methodology4 results

Anomaly DetectiononMVTec AD
Detection AUROC· 2025-03-04
99.8
best: 99.9 (GLASS)
Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection arXiv:2503.02424
Anomaly DetectiononMVTec AD
Segmentation AP· 2025-03-04
72.1
best: 87.6 (WeakREST-Block)
Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection arXiv:2503.02424
Anomaly DetectiononMVTec AD
Segmentation AUPRO· 2025-03-04
95.6
best: 98.4 (WeakREST-Block)
Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection arXiv:2503.02424
Anomaly DetectiononMVTec AD
Segmentation AUROC· 2025-03-04
98.6
best: 99.7 (WeakREST-Block)
Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection arXiv:2503.02424