Out-of-Distribution Detection on ImageNet-1K vs Textures
29.46FPR95ViM
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ViMBackbone=Swin-T, ID Accuracy=81.60%2026.04 | 29.46 | 92.69 | |
| Energy Profile Divergence (EPD)Backbone=Swin-T, ID Accuracy=81.60%2026.04 | 32.64 | 90.86 | |
| KNNBackbone=Swin-T, ID Accuracy=81.60%2026.04 | 35.79 | 90.56 | |
| MDSBackbone=Swin-T, ID Accuracy=81.60%2026.04 | 37.47 | 89.82 | |
| RMDSBackbone=Swin-T, ID Accuracy=81.60%2026.04 | 39.09 | 89.26 | |
| GENBackbone=Swin-T, ID Accuracy=81.60%2026.04 | 45.04 | 88.16 | |
| SHEBackbone=Swin-T, ID Accuracy=81.60%2026.04 | 51.32 | 88.86 | |
| ReActBackbone=Swin-T, ID Accuracy=81.60%2026.04 | 53.98 | 87.04 | |
| MSPBackbone=Swin-T, ID Accuracy=81.60%2026.04 | 61.49 | 83.27 | |
| TempScaleBackbone=Swin-T, ID Accuracy=81.60%2026.04 | 62.89 | 83.68 | |
| OpenMaxBackbone=Swin-T, ID Accuracy=81.60%2026.04 | 76.41 | 82.81 | |
| MLSBackbone=Swin-T, ID Accuracy=81.60%2026.04 | 79.94 | 81.7 | |
| EBOBackbone=Swin-T, ID Accuracy=81.60%2026.04 | 84.29 | 79 | |
| DICEBackbone=Swin-T, ID Accuracy=81.60%2026.04 | 87.37 | 77.61 | |
| ASHBackbone=Swin-T, ID Accuracy=81.60%2026.04 | 96.17 | 41.32 | |
| GradNormBackbone=Swin-T, ID Accuracy=81.60%2026.04 | 97.8 | 34.75 |