DRAEM+SSPCAB

Reported on 3 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.

Methodology3 results

Anomaly DetectiononMVTec AD
Segmentation AP· uses extra data· 2021-11-17
69.9
best: 87.6 (WeakREST-Block)
SOTA
Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection arXiv:2111.09099
Anomaly DetectiononMVTec AD
Detection AUROC· uses extra data· 2021-11-17
98.9
best: 99.9 (GLASS)
Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection arXiv:2111.09099
Anomaly DetectiononMVTec AD
Segmentation AUROC· uses extra data· 2021-11-17
97.2
best: 99.7 (WeakREST-Block)
Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection arXiv:2111.09099