VAN-Large (HamNet)

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)· 2022-02-20
55
best: 3000 (FD-SwinV2-G)
Visual Attention Network arXiv:2202.09741
Semantic SegmentationonADE20K
Validation mIoU· 2022-02-20
50.2
best: 63.6 (ViT-P (InternImage-H))
Visual Attention Network arXiv:2202.09741

Audio2 results

10-shot image generationonADE20K
Params (M)· 2022-02-20
55
best: 3000 (FD-SwinV2-G)
Visual Attention Network arXiv:2202.09741
10-shot image generationonADE20K
Validation mIoU· 2022-02-20
50.2
best: 63.6 (ViT-P (InternImage-H))
Visual Attention Network arXiv:2202.09741