Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/SegFormer-B0

SegFormer-B0

Reported on 12 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.

Medical6 results

Semantic SegmentationonCityscapes val
Validation mIoU· 2021-05-31
76.2
best: 87.35 (SERNet-Former)
SOTA
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
Semantic Segmentationon US3D
mIoU· 2021-05-31
71.8
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
83.67
best: 86.39 (LMFNet-3)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
Semantic SegmentationonVaihingen
mIoU· 2021-05-31
75.57
best: 82.87 (CMX)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
Semantic SegmentationonADE20K
Params (M)· uses extra data· 2021-05-31
3.8
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
37.4
best: 63.6 (ViT-P (InternImage-H))
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203

Audio6 results

10-shot image generationonCityscapes val
Validation mIoU· 2021-05-31
76.2
best: 87.35 (SERNet-Former)
SOTA
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
10-shot image generationon US3D
mIoU· 2021-05-31
71.8
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
83.67
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
75.57
best: 82.87 (CMX)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
10-shot image generationonADE20K
Params (M)· uses extra data· 2021-05-31
3.8
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
37.4
best: 63.6 (ViT-P (InternImage-H))
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203