LV-ViT-L (UperNet, MS)

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

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)· 2021-04-22
209
best: 3000 (FD-SwinV2-G)
SOTA
All Tokens Matter: Token Labeling for Training Better Vision Transformers arXiv:2104.10858
Semantic SegmentationonADE20K
Validation mIoU· 2021-04-22
51.8
best: 63.6 (ViT-P (InternImage-H))
All Tokens Matter: Token Labeling for Training Better Vision Transformers arXiv:2104.10858

Audio2 results

10-shot image generationonADE20K
Params (M)· 2021-04-22
209
best: 3000 (FD-SwinV2-G)
SOTA
All Tokens Matter: Token Labeling for Training Better Vision Transformers arXiv:2104.10858
10-shot image generationonADE20K
Validation mIoU· 2021-04-22
51.8
best: 63.6 (ViT-P (InternImage-H))
All Tokens Matter: Token Labeling for Training Better Vision Transformers arXiv:2104.10858