Table 6 Abnormal detection and localization results on magnetic tiles.
From: A novel dual-student reverse knowledge distillation method for magnetic tile defect detection
Model | Image Auroc | Pixel Auroc | Pixel Aupro | Image F1 | Image ACC |
|---|---|---|---|---|---|
FOD | 0.907 | 0.841 | 0.539 | 0.902 | 0.932 |
CKAAD | 0.853 | 0.746 | 0.555 | 0.839 | 0.795 |
SimpleNet | 0.912 | 0.917 | 0.472 | 0.916 | 0.849 |
PBAS | 0.836 | 0.815 | 0.461 | 0.912 | 0.836 |
FastFlow | 0.758 | 0.782 | 0.351 | 0.787 | 0.726 |
RD4AD | 0.815 | 0.852 | 0.558 | 0.931 | 0.877 |
IKD | 0.881 | 0.87 | 0.532 | 0.878 | 0.932 |
BSDRD | 0.904 | 0.931 | 0.615 | 0.938 | 0.945 |