OOD Detection on CIFAR-10 SCOOD Benchmark Average
8.53FPR95ET-OOD
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| ET-OODBackbone=ResNet-18, Extra Unlabeled Training Data=Tiny-ImageNet2023.03 | 8.53 | 96.47 | 97.1 | 95.65 | 40.31 | 63.95 | 77.35 | 86.27 | |
| UDGBackbone=ResNet-18, Extra Unlabeled Training Data=Tiny-ImageNet2023.03 | 36.22 | 93.78 | 93.61 | 92.61 | 13.87 | 34.48 | 59.97 | 82.14 | |
| EBOBackbone=ResNet-18, Extra Unlabeled Training Data=None2023.03 | 50.03 | 83.83 | 77.15 | 85.11 | 0.49 | 1.93 | 9.12 | 46.48 | |
| OEBackbone=ResNet-18, Extra Unlabeled Training Data=Tiny-ImageNet2023.03 | 50.53 | 88.93 | 87.55 | 87.83 | 13.41 | 20.25 | 33.91 | 68.2 | |
| ODINBackbone=ResNet-18, Extra Unlabeled Training Data=None2023.03 | 52 | 82 | 73.13 | 85.12 | 0.36 | 1.29 | 6.92 | 39.37 | |
| MCDBackbone=ResNet-18, Extra Unlabeled Training Data=Tiny-ImageNet2023.03 | 73.02 | 83.89 | 83.39 | 80.53 | 5.41 | 12.3 | 28.02 | 62.02 |