CAFormer-B36 (384)

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-R
Top-1 Error Rate· 2022-10-24
45
best: 3.9 (Model soups (BASIC-L))
MetaFormer Baselines for Vision arXiv:2210.13452
Domain AdaptationonImageNet-A
Top-1 accuracy %· 2022-10-24
61.9
best: 94.17 (Model soups (BASIC-L))
MetaFormer Baselines for Vision arXiv:2210.13452

Computer Vision2 results

Domain GeneralizationonImageNet-R
Top-1 Error Rate· 2022-10-24
45
best: 3.9 (Model soups (BASIC-L))
MetaFormer Baselines for Vision arXiv:2210.13452
Domain GeneralizationonImageNet-A
Top-1 accuracy %· 2022-10-24
61.9
best: 94.17 (Model soups (BASIC-L))
MetaFormer Baselines for Vision arXiv:2210.13452