GFNet-S

Reported on 4 benchmarks across 2 tasks · 1 paper

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

Methodology2 results

Domain AdaptationonImageNet-A
Top-1 accuracy %· 2021-07-01
14.3
best: 94.17 (Model soups (BASIC-L))
Global Filter Networks for Image Classification arXiv:2107.00645
Domain AdaptationonImageNet-C
mean Corruption Error (mCE)· 2021-07-01
53.8
best: 22 (EfficientNet-L2+RPL)
Global Filter Networks for Image Classification arXiv:2107.00645

Computer Vision2 results

Domain GeneralizationonImageNet-A
Top-1 accuracy %· 2021-07-01
14.3
best: 94.17 (Model soups (BASIC-L))
Global Filter Networks for Image Classification arXiv:2107.00645
Domain GeneralizationonImageNet-C
mean Corruption Error (mCE)· 2021-07-01
53.8
best: 28.2 (DINOv2 (ViT-g/14, frozen model, linear eval))
Global Filter Networks for Image Classification arXiv:2107.00645