ResNet50, BatchNorm adaptation

Reported on 2 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology1 result

Domain AdaptationonImageNet-R
Top 1 Error· 2020-06-30
59.9
best: 4.54 (Model soups (ViT-G/14))
SOTA
Improving robustness against common corruptions by covariate shift adaptation arXiv:2006.16971

Other1 result

Unsupervised Domain AdaptationonImageNet-R
Top 1 Error· 2020-06-30
59.9
best: 4.54 (Model soups (ViT-G/14))
SOTA
Improving robustness against common corruptions by covariate shift adaptation arXiv:2006.16971