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

SegFormer

Reported on 18 benchmarks across 4 tasks · 1 paper · 10 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical8 results

Semantic SegmentationonDELIVER
mIoU· 2021-05-31
57.2
best: 67.8 (CAFuser)
SOTA
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
Semantic SegmentationonFine-Grained Grass Segmentation Dataset
mIoU· 2021-05-31
48.29
best: 51.96 (D2LS)
SOTA
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
Semantic Segmentationon Synthetic Bathing Perception
mIoU· 2021-05-31
86.86
best: 94.2 (CMX-SRA)
SOTA
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
Semantic SegmentationonSELMA
mIoU· 2021-05-31
77.2
best: 91.7 (CMX)
SOTA
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
Semantic SegmentationonUrbanLF
mIoU (Real)· 2021-05-31
82.2
best: 83.22 (CMNeXt (RGB-LF8))
SOTA
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
Semantic SegmentationonUrbanLF
mIoU (Syn)· 2021-05-31
78.53
best: 81.02 (CMNeXt (RGB-LF80))
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
Semantic SegmentationonRGB-T-Glass-Segmentation
MAE· 2021-05-31
0.053
best: 0.024 (RGB-T-Glass-Segmentation)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
Semantic SegmentationonCrackVision12K
mIoU· 2021-05-31
0.57969
best: 0.62982 (Hybrid-Segmentor)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203

Audio8 results

10-shot image generationonDELIVER
mIoU· 2021-05-31
57.2
best: 67.8 (CAFuser)
SOTA
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
10-shot image generationonFine-Grained Grass Segmentation Dataset
mIoU· 2021-05-31
48.29
best: 51.96 (D2LS)
SOTA
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
10-shot image generationon Synthetic Bathing Perception
mIoU· 2021-05-31
86.86
best: 94.2 (CMX-SRA)
SOTA
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
10-shot image generationonSELMA
mIoU· 2021-05-31
77.2
best: 91.7 (CMX)
SOTA
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
10-shot image generationonUrbanLF
mIoU (Real)· 2021-05-31
82.2
best: 83.22 (CMNeXt (RGB-LF8))
SOTA
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
10-shot image generationonUrbanLF
mIoU (Syn)· 2021-05-31
78.53
best: 81.02 (CMNeXt (RGB-LF80))
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
10-shot image generationonRGB-T-Glass-Segmentation
MAE· 2021-05-31
0.053
best: 0.024 (RGB-T-Glass-Segmentation)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203
10-shot image generationonCrackVision12K
mIoU· 2021-05-31
0.57969
best: 0.62982 (Hybrid-Segmentor)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203

Computer Vision1 result

Scene SegmentationonRGB-T-Glass-Segmentation
MAE· 2021-05-31
0.053
best: 0.024 (RGB-T-Glass-Segmentation)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203

Methodology1 result

2D Object DetectiononRGB-T-Glass-Segmentation
MAE· 2021-05-31
0.053
best: 0.024 (RGB-T-Glass-Segmentation)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers arXiv:2105.15203