Anomaly Detection On Surface Defect Saliency
Metrics
Detection AUROC
Results
Performance results of various models on this benchmark
| Paper Title | ||
|---|---|---|
| HETMM | 99.5 | Hard-normal Example-aware Template Mutual Matching for Industrial Anomaly Detection |
| CS-Flow (unsupervised) | 99.3 | Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection |
| DifferNet (unsupervised) | 97.7 | Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows |
| MCuePush (supervised) | - | Surface Defect Saliency of Magnetic Tile |
0 of 4 row(s) selected.