FCDD

Reported on 2 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.

Methodology2 results

Anomaly DetectiononOne-class ImageNet-30
AUROC· uses extra data· 2020-07-03
91
best: 99.9 (BCE-Clip (OE))
SOTA
Explainable Deep One-Class Classification arXiv:2007.01760
Anomaly DetectiononOne-class CIFAR-10
AUROC· uses extra data· 2020-07-03
92
best: 99.6 (CLIP (OE))
Explainable Deep One-Class Classification arXiv:2007.01760