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/DiNAT-L (Mask2Former)

DiNAT-L (Mask2Former)

Reported on 13 benchmarks across 3 tasks · 1 paper

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

Medical6 results

Semantic SegmentationonCityscapes val
mIoU· 2022-09-29
84.5
best: 90.3 (EfficientPS (Cityscapes-fine))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Semantic SegmentationonADE20K val
mIoU· 2022-09-29
58.1
best: 62.8 (BEiT-3)
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Semantic SegmentationonADE20K
Validation mIoU· 2022-09-29
58.1
best: 63.6 (ViT-P (InternImage-H))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Semantic SegmentationonCityscapes val
AP· 2022-09-29
44.5
best: 50.6 (ViT-P (OneFormer, InternImage-H))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Semantic SegmentationonCityscapes val
PQ· 2022-09-29
67.2
best: 70.8 (ViT-P (OneFormer, InternImage-H))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Semantic SegmentationonCityscapes val
mIoU· 2022-09-29
83.4
best: 90.3 (EfficientPS (Cityscapes-fine))
Dilated Neighborhood Attention Transformer arXiv:2209.15001

Audio6 results

10-shot image generationonCityscapes val
mIoU· 2022-09-29
84.5
best: 90.3 (EfficientPS (Cityscapes-fine))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
10-shot image generationonADE20K val
mIoU· 2022-09-29
58.1
best: 62.8 (BEiT-3)
Dilated Neighborhood Attention Transformer arXiv:2209.15001
10-shot image generationonADE20K
Validation mIoU· 2022-09-29
58.1
best: 63.6 (ViT-P (InternImage-H))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
10-shot image generationonCityscapes val
AP· 2022-09-29
44.5
best: 50.6 (ViT-P (OneFormer, InternImage-H))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
10-shot image generationonCityscapes val
PQ· 2022-09-29
67.2
best: 70.8 (ViT-P (OneFormer, InternImage-H))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
10-shot image generationonCityscapes val
mIoU· 2022-09-29
83.4
best: 90.3 (EfficientPS (Cityscapes-fine))
Dilated Neighborhood Attention Transformer arXiv:2209.15001

Computer Vision3 results

Panoptic SegmentationonCityscapes val
AP· 2022-09-29
44.5
best: 50.6 (ViT-P (OneFormer, InternImage-H))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Panoptic SegmentationonCityscapes val
PQ· 2022-09-29
67.2
best: 70.8 (ViT-P (OneFormer, InternImage-H))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Panoptic SegmentationonCityscapes val
mIoU· 2022-09-29
83.4
best: 90.3 (EfficientPS (Cityscapes-fine))
Dilated Neighborhood Attention Transformer arXiv:2209.15001