Unsupervised Domain Adaptation On Imagenet R
评估指标
Top 1 Error
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | ||
|---|---|---|---|
| ResNet50, BatchNorm adaptation | 59.9 | Improving robustness against common corruptions by covariate shift adaptation | |
| ResNet50 + ENT | 56.1 | If your data distribution shifts, use self-learning | |
| ResNet50 + RPL | 54.1 | If your data distribution shifts, use self-learning | |
| ResNet50+DeepAug+Augmix, BatchNorm adaptation | 48.9 | Improving robustness against common corruptions by covariate shift adaptation | |
| ResNeXt101+DeepAug+AugMix, BatchNorm Adaptation, | 44.0 | Improving robustness against common corruptions by covariate shift adaptation | |
| 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 | |
| Model soups (ViT-G/14) | 4.54 | Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time |
0 of 8 row(s) selected.