Semi-orthogonal

Reported on 5 benchmarks across 2 tasks · 1 paper · 5 SOTA

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

Methodology3 results

Anomaly DetectiononMVTec AD
Segmentation AUROC· 2021-05-31
98.2
best: 99.7 (WeakREST-Block)
SOTA
Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation arXiv:2105.14737
Anomaly DetectiononKolektorSDD
Segmentation AUROC· uses extra data· 2021-05-31
96
SOTA
Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation arXiv:2105.14737
Anomaly DetectiononKolektorSDD2
Segmentation AUROC· uses extra data· 2021-05-31
98.1
best: 99.7 (WeakREST-Un)
SOTA
Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation arXiv:2105.14737

Graphs2 results

Unsupervised Anomaly DetectiononKolektorSDD
Segmentation AUROC· uses extra data· 2021-05-31
96
SOTA
Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation arXiv:2105.14737
Unsupervised Anomaly DetectiononKolektorSDD2
Segmentation AUROC· uses extra data· 2021-05-31
98.1
best: 99.7 (WeakREST-Un)
SOTA
Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation arXiv:2105.14737