Light-Ham (VAN-Small, D=256)

Reported on 6 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.

Medical3 results

Semantic SegmentationonADE20K
GFLOPs (512 x 512)· 2021-09-09
15.8
best: 3335 (ConvNeXt-XL++)
Is Attention Better Than Matrix Decomposition?arXiv:2109.04553
Semantic SegmentationonADE20K
Params (M)· 2021-09-09
13.8
best: 3000 (FD-SwinV2-G)
Is Attention Better Than Matrix Decomposition?arXiv:2109.04553
Semantic SegmentationonADE20K
Validation mIoU· 2021-09-09
45.2
best: 63.6 (ViT-P (InternImage-H))
Is Attention Better Than Matrix Decomposition?arXiv:2109.04553

Audio3 results

10-shot image generationonADE20K
GFLOPs (512 x 512)· 2021-09-09
15.8
best: 3335 (ConvNeXt-XL++)
Is Attention Better Than Matrix Decomposition?arXiv:2109.04553
10-shot image generationonADE20K
Params (M)· 2021-09-09
13.8
best: 3000 (FD-SwinV2-G)
Is Attention Better Than Matrix Decomposition?arXiv:2109.04553
10-shot image generationonADE20K
Validation mIoU· 2021-09-09
45.2
best: 63.6 (ViT-P (InternImage-H))
Is Attention Better Than Matrix Decomposition?arXiv:2109.04553