DisAug CLR

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 DetectiononOne-class CIFAR-100
AUROC· 2020-11-04
86.5
best: 98.4 (GeneralAD)
Learning and Evaluating Representations for Deep One-class Classification arXiv:2011.02578
Anomaly DetectiononOne-class CIFAR-10
AUROC· 2020-11-04
92.5
best: 99.6 (CLIP (OE))
Learning and Evaluating Representations for Deep One-class Classification arXiv:2011.02578
Anomaly DetectiononMVTec AD
Detection AUROC· 2020-11-04
86.5
best: 99.9 (GLASS)
Learning and Evaluating Representations for Deep One-class Classification arXiv:2011.02578
Anomaly DetectiononMVTec AD
Segmentation AUROC· 2020-11-04
90.4
best: 99.7 (WeakREST-Block)
Learning and Evaluating Representations for Deep One-class Classification arXiv:2011.02578