SegFormer-B1

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 Segmentationon US3D
mIoU· 2021-05-31
74.19
best: 85.09 (LMFNet-3)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
Semantic Segmentationon Potsdam
mIoU· 2021-05-31
84.37
best: 86.39 (LMFNet-3)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
Semantic SegmentationonVaihingen
mIoU· 2021-05-31
76.92
best: 82.87 (CMX)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203

Audio3 results

10-shot image generationon US3D
mIoU· 2021-05-31
74.19
best: 85.09 (LMFNet-3)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
10-shot image generationon Potsdam
mIoU· 2021-05-31
84.37
best: 86.39 (LMFNet-3)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
10-shot image generationonVaihingen
mIoU· 2021-05-31
76.92
best: 82.87 (CMX)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203