OOD detection on MVTec Metal Nut - Similar artifacts
85.11AUROC (%)Residual
Evaluation results
| Method | Links | |
|---|---|---|
| ResidualBackbone=VGG16, Method category=Feature-based, Hyperparameter selection=best-performing2026.02 | 85.11 | |
| NMDBackbone=VGG16, Method category=Feature-based, Hyperparameter selection=best-performing2026.02 | 82.16 | |
| KNNBackbone=VGG16, Method category=Feature-based, Hyperparameter selection=best-performing2026.02 | 80.57 | |
| ODINBackbone=VGG16, Method category=Confidence-based, Hyperparameter selection=best-performing2026.02 | 78.07 | |
| Deep EnsembleBackbone=VGG16, Method category=Confidence-based, Hyperparameter selection=best-performing2026.02 | 76.77 | |
| DICEBackbone=VGG16, Method category=Confidence-based, Hyperparameter selection=best-performing2026.02 | 75.91 | |
| ViMBackbone=VGG16, Method category=Confidence-based, Hyperparameter selection=best-performing2026.02 | 75.91 | |
| WeiPerBackbone=VGG16, Method category=Confidence-based, Hyperparameter selection=best-performing2026.02 | 75.34 | |
| ReActBackbone=VGG16, Method category=Confidence-based, Hyperparameter selection=best-performing2026.02 | 75.23 | |
| PCXBackbone=VGG16, Method category=Feature-based, Hyperparameter selection=best-performing2026.02 | 74.97 | |
| XOOD-MBackbone=VGG16, Method category=Feature-based, Hyperparameter selection=best-performing2026.02 | 74.2 | |
| MCPBackbone=VGG16, Method category=Confidence-based, Hyperparameter selection=best-performing2026.02 | 73.98 | |
| MC-DropoutBackbone=VGG16, Method category=Confidence-based, Hyperparameter selection=best-performing2026.02 | 72.89 | |
| GRAMBackbone=VGG16, Method category=Feature-based, Hyperparameter selection=best-performing2026.02 | 72.46 | |
| ASHBackbone=VGG16, Method category=Confidence-based, Hyperparameter selection=best-performing2026.02 | 70.8 | |
| LOFBackbone=VGG16, Method category=Feature-based, Hyperparameter selection=best-performing2026.02 | 70 | |
| KDE (Gaussian)Backbone=VGG16, Method category=Feature-based, Hyperparameter selection=best-performing2026.02 | 69.89 | |
| CoPBackbone=VGG16, Method category=Feature-based, Hyperparameter selection=best-performing2026.02 | 68.18 | |
| SHEBackbone=VGG16, Method category=Confidence-based, Hyperparameter selection=best-performing2026.02 | 67.05 | |
| CoRPBackbone=VGG16, Method category=Feature-based, Hyperparameter selection=best-performing2026.02 | 63.63 | |
| GradNormBackbone=VGG16, Method category=Confidence-based, Hyperparameter selection=best-performing2026.02 | 63.14 | |
| MBMBackbone=VGG16, Method category=Feature-based, Hyperparameter selection=best-performing2026.02 | 61.28 | |
| NuSABackbone=VGG16, Method category=Feature-based, Hyperparameter selection=best-performing2026.02 | 61.16 | |
| MahalanobisBackbone=VGG16, Method category=Feature-based, Hyperparameter selection=best-performing2026.02 | 60.8 | |
| GradOrthBackbone=VGG16, Method category=Confidence-based, Hyperparameter selection=best-performing2026.02 | 59.09 | |
| FeatureNormBackbone=VGG16, Method category=Feature-based, Hyperparameter selection=best-performing2026.02 | 57.95 | |
| GAIA-ABackbone=VGG16, Method category=Confidence-based, Hyperparameter selection=best-performing2026.02 | 55.57 | |
| NANBackbone=VGG16, Method category=Feature-based, Hyperparameter selection=best-performing2026.02 | 53.98 | |
| TAPUUDBackbone=VGG16, Method category=Feature-based, Hyperparameter selection=best-performing2026.02 | 52.36 | |
| NACBackbone=VGG16, Method category=Feature-based, Hyperparameter selection=best-performing2026.02 | 43.53 |