OOD Detection on Near-OOD Average
65.23FPR@95EPD
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| EPDBackbone=ViT-B/16, ID Accuracy=81.14%, ID Dataset=ImageNet-1K2026.04 | 65.23 | 78.98 | |
| RMDSBackbone=ViT-B/16, ID Accuracy=81.14%, ID Dataset=ImageNet-1K2026.04 | 65.38 | 80.09 | |
| MDSBackbone=ViT-B/16, ID Accuracy=81.14%, ID Dataset=ImageNet-1K2026.04 | 66.11 | 79.04 | |
| KNNBackbone=ViT-B/16, ID Accuracy=81.14%, ID Dataset=ImageNet-1K2026.04 | 70.48 | 74.11 | |
| GENBackbone=ViT-B/16, ID Accuracy=81.14%, ID Dataset=ImageNet-1K2026.04 | 70.78 | 76.3 | |
| SHEBackbone=ViT-B/16, ID Accuracy=81.14%, ID Dataset=ImageNet-1K2026.04 | 70.88 | 76.11 | |
| ViMBackbone=ViT-B/16, ID Accuracy=81.14%, ID Dataset=ImageNet-1K2026.04 | 73.76 | 77.03 | |
| MSPBackbone=ViT-B/16, ID Accuracy=81.14%, ID Dataset=ImageNet-1K2026.04 | 81.88 | 73.53 | |
| ReActBackbone=ViT-B/16, ID Accuracy=81.14%, ID Dataset=ImageNet-1K2026.04 | 84.48 | 69.27 | |
| TempScaleBackbone=ViT-B/16, ID Accuracy=81.14%, ID Dataset=ImageNet-1K2026.04 | 84.63 | 73.18 | |
| DICEBackbone=ViT-B/16, ID Accuracy=81.14%, ID Dataset=ImageNet-1K2026.04 | 85.43 | 65.36 | |
| OpenMaxBackbone=ViT-B/16, ID Accuracy=81.14%, ID Dataset=ImageNet-1K2026.04 | 88.78 | 73.64 | |
| MLSBackbone=ViT-B/16, ID Accuracy=81.14%, ID Dataset=ImageNet-1K2026.04 | 92.25 | 68.3 | |
| EBOBackbone=ViT-B/16, ID Accuracy=81.14%, ID Dataset=ImageNet-1K2026.04 | 93.21 | 62.41 | |
| ASHBackbone=ViT-B/16, ID Accuracy=81.14%, ID Dataset=ImageNet-1K2026.04 | 94.45 | 53.2 | |
| GradNormBackbone=ViT-B/16, ID Accuracy=81.14%, ID Dataset=ImageNet-1K2026.04 | 94.72 | 53.68 |