Image Classification on CIFAR-100-C (test)
73Gaussian AccuracySource
Evaluation results
| Method | Links | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| SourceBackbone=ResNeXt-29, Corruption Severity Level=52022.03 | 73 | 68 | 39.4 | 29.3 | 54.1 | 30.8 | 28.8 | 39.5 | 45.8 | 50.3 | 29.5 | 55.1 | 37.2 | 74.7 | 41.2 | 46.4 | |
| BN Stats AdaptBackbone=ResNeXt-29, Corruption Severity Level=52022.03 | 42.1 | 40.7 | 42.7 | 27.6 | 41.9 | 29.7 | 27.9 | 34.9 | 35 | 41.5 | 26.5 | 30.3 | 35.7 | 32.9 | 41.2 | 35.4 | |
| CoTTABackbone=ResNeXt-29, Corruption Severity Level=52022.03 | 40.1 | 37.7 | 39.7 | 26.9 | 38 | 27.9 | 26.4 | 32.8 | 31.8 | 40.3 | 24.7 | 26.9 | 32.5 | 28.3 | 33.5 | 32.5 | |
| Pseudo-labelBackbone=ResNeXt-29, Corruption Severity Level=52022.03 | 38.1 | 36.1 | 40.7 | 33.2 | 45.9 | 38.3 | 36.4 | 44 | 45.6 | 52.8 | 45.2 | 53.5 | 60.1 | 58.1 | 64.5 | 46.2 | |
| TENT-continualBackbone=ResNeXt-29, Corruption Severity Level=52022.03 | 37.2 | 35.8 | 41.7 | 37.9 | 51.2 | 48.3 | 48.5 | 58.4 | 63.7 | 71.1 | 70.4 | 82.3 | 88 | 88.5 | 90.4 | 60.9 |