| Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time | ✓ Link | 4.54 | Model soups (ViT-G/14) | 2022-03-10 |
| If your data distribution shifts, use self-learning | ✓ Link | 17.4 | EfficientNet-L2 Noisy Student + RPL | 2021-04-27 |
| If your data distribution shifts, use self-learning | ✓ Link | 19.7 | EfficientNet-L2 Noisy Student + ENT | 2021-04-27 |
| Improving robustness against common corruptions by covariate shift adaptation | ✓ Link | 44.0 | ResNeXt101+DeepAug+AugMix, BatchNorm Adaptation, | 2020-06-30 |
| Improving robustness against common corruptions by covariate shift adaptation | ✓ Link | 48.9 | ResNet50+DeepAug+Augmix, BatchNorm adaptation | 2020-06-30 |
| If your data distribution shifts, use self-learning | ✓ Link | 54.1 | ResNet50 + RPL | 2021-04-27 |
| If your data distribution shifts, use self-learning | ✓ Link | 56.1 | ResNet50 + ENT | 2021-04-27 |
| Improving robustness against common corruptions by covariate shift adaptation | ✓ Link | 59.9 | ResNet50, BatchNorm adaptation | 2020-06-30 |