Unsupervised Domain Adaptation On Imagenet R
Metrics
Top 1 Error
Results
Performance results of various models on this benchmark
Model Name | Top 1 Error | Paper Title | Repository |
|---|---|---|---|
| ResNet50+DeepAug+Augmix, BatchNorm adaptation | 48.9 | Improving robustness against common corruptions by covariate shift adaptation | |
| ResNet50 + RPL | 54.1 | If your data distribution shifts, use self-learning | |
| ResNet50, BatchNorm adaptation | 59.9 | Improving robustness against common corruptions by covariate shift adaptation | |
| Model soups (ViT-G/14) | 4.54 | Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time | |
| EfficientNet-L2 Noisy Student + ENT | 19.7 | If your data distribution shifts, use self-learning | |
| EfficientNet-L2 Noisy Student + RPL | 17.4 | If your data distribution shifts, use self-learning | |
| ResNet50 + ENT | 56.1 | If your data distribution shifts, use self-learning | |
| ResNeXt101+DeepAug+AugMix, BatchNorm Adaptation, | 44.0 | Improving robustness against common corruptions by covariate shift adaptation |
0 of 8 row(s) selected.