SegFormer-B5

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)· uses extra data· 2021-05-31
84.7
best: 3000 (FD-SwinV2-G)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
Semantic SegmentationonADE20K
Validation mIoU· uses extra data· 2021-05-31
51.8
best: 63.6 (ViT-P (InternImage-H))
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203

Audio2 results

10-shot image generationonADE20K
Params (M)· uses extra data· 2021-05-31
84.7
best: 3000 (FD-SwinV2-G)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
10-shot image generationonADE20K
Validation mIoU· uses extra data· 2021-05-31
51.8
best: 63.6 (ViT-P (InternImage-H))
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203