DeepAugment (ResNet-50)

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Methodology2 results

Domain AdaptationonImageNet-R
Top-1 Error Rate· 2020-06-29
57.8
best: 3.9 (Model soups (BASIC-L))
SOTA
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization arXiv:2006.16241
Domain AdaptationonImageNet-C
mean Corruption Error (mCE)· 2020-06-29
60.4
best: 22 (EfficientNet-L2+RPL)
SOTA
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization arXiv:2006.16241

Computer Vision2 results

Domain GeneralizationonImageNet-R
Top-1 Error Rate· 2020-06-29
57.8
best: 3.9 (Model soups (BASIC-L))
SOTA
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization arXiv:2006.16241
Domain GeneralizationonImageNet-C
mean Corruption Error (mCE)· 2020-06-29
60.4
best: 28.2 (DINOv2 (ViT-g/14, frozen model, linear eval))
SOTA
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization arXiv:2006.16241