ViT-Adapter-L (Mask2Former, BEiTv2 pretrain)

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 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)· uses extra data· 2022-05-17
571
best: 3000 (FD-SwinV2-G)
SOTA
Vision Transformer Adapter for Dense Predictions arXiv:2205.08534
Semantic SegmentationonADE20K
Validation mIoU· uses extra data· 2022-05-17
61.5
best: 63.6 (ViT-P (InternImage-H))
SOTA
Vision Transformer Adapter for Dense Predictions arXiv:2205.08534

Audio2 results

10-shot image generationonADE20K
Params (M)· uses extra data· 2022-05-17
571
best: 3000 (FD-SwinV2-G)
SOTA
Vision Transformer Adapter for Dense Predictions arXiv:2205.08534
10-shot image generationonADE20K
Validation mIoU· uses extra data· 2022-05-17
61.5
best: 63.6 (ViT-P (InternImage-H))
SOTA
Vision Transformer Adapter for Dense Predictions arXiv:2205.08534