TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Unsupervised Domain Adaptation/ImageNet-C

Unsupervised Domain Adaptation on ImageNet-C

Metric: mean Corruption Error (mCE) (lower is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕mean Corruption Error (mCE)▲Extra DataPaperDate↕Code
1EfficientNet-L2+RPL22YesIf your data distribution shifts, use self-learn...2021-04-27Code
2EfficientNet-L2+ENT23YesIf your data distribution shifts, use self-learn...2021-04-27Code
3ResNeXt101 32x8d + DeepAug + Augmix + RPL34.8NoIf your data distribution shifts, use self-learn...2021-04-27Code
4ResNeXt101 32x8d + DeepAug + Augmix + ENT35.5NoIf your data distribution shifts, use self-learn...2021-04-27Code
5ResNeXt101+DeepAug+AugMix, BatchNorm Adaptation, full adaptation38NoImproving robustness against common corruptions ...2020-06-30Code
6ResNeXt101+DeepAug+AugMix, BatchNorm Adaptation, 8 samples40.7NoImproving robustness against common corruptions ...2020-06-30Code
7ResNeXt101 32x8d + IG-3.5B + ENT40.8YesIf your data distribution shifts, use self-learn...2021-04-27Code
8ResNeXt101 32x8d + IG-3.5B + RPL40.9YesIf your data distribution shifts, use self-learn...2021-04-27Code
9ResNeXt101 32x8d + RPL43.2NoIf your data distribution shifts, use self-learn...2021-04-27Code
10ResNeXt101 32x8d + ENT44.3NoIf your data distribution shifts, use self-learn...2021-04-27Code
11ResNet50+DeepAug+AugMix, BatchNorm Adaptation, full adaptation45.4NoImproving robustness against common corruptions ...2020-06-30Code
12ResNet50+DeepAug+AugMix, BatchNorm Adaptation, 8 samples48.4NoImproving robustness against common corruptions ...2020-06-30Code
13ResNet50 + RPL50.5NoIf your data distribution shifts, use self-learn...2021-04-27Code
14ResNet50 + ENT51.6NoIf your data distribution shifts, use self-learn...2021-04-27Code
15ResNet50 (baseline), BatchNorm Adaptation, full adaptation62.2NoImproving robustness against common corruptions ...2020-06-30Code
16ResNet50 (baseline), BatchNorm Adaptation, 8 samples65NoImproving robustness against common corruptions ...2020-06-30Code