A2MIM (ResNet-50)

Reported on 2 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.

Medical1 result

Semantic SegmentationonADE20K
Validation mIoU· 2022-05-27
38.3
best: 63.6 (ViT-P (InternImage-H))
Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN arXiv:2205.13943

Audio1 result

10-shot image generationonADE20K
Validation mIoU· 2022-05-27
38.3
best: 63.6 (ViT-P (InternImage-H))
Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN arXiv:2205.13943