tiny-MOAT-2 (IN-1K pretraining, single scale)

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.

Medical2 results

Semantic SegmentationonADE20K
Params (M)· 2022-10-04
13
best: 3000 (FD-SwinV2-G)
MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models arXiv:2210.01820
Semantic SegmentationonADE20K
Validation mIoU· 2022-10-04
44.9
best: 63.6 (ViT-P (InternImage-H))
MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models arXiv:2210.01820

Audio2 results

10-shot image generationonADE20K
Params (M)· 2022-10-04
13
best: 3000 (FD-SwinV2-G)
MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models arXiv:2210.01820
10-shot image generationonADE20K
Validation mIoU· 2022-10-04
44.9
best: 63.6 (ViT-P (InternImage-H))
MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models arXiv:2210.01820