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 (single-scale, Mask2Former)

DiNAT-L (single-scale, Mask2Former)

Reported on 19 benchmarks across 4 tasks · 1 paper · 6 SOTA

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

Computer Vision9 results

Instance SegmentationonCOCO minival
AP50· 2022-09-29
75
best: 80.1 (InternImage-H)
SOTA
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Instance SegmentationonCityscapes val
AP50· 2022-09-29
72.6
best: 74.2 (AFF-Base (single-scale, point-based Mask2Former))
SOTA
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Instance SegmentationonCityscapes val
mask AP· 2022-09-29
45.1
best: 49 (ViT-P (OneFormer, ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
SOTA
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Panoptic SegmentationonCOCO minival
mIoU· 2022-09-29
68.3
best: 69.7 (UMG-CLIP-E/14)
SOTA
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Instance SegmentationonCOCO minival
mask AP· 2022-09-29
50.8
best: 56.6 (Co-DETR)
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Panoptic SegmentationonCOCO minival
AP· 2022-09-29
49.2
best: 53.2 (OpenSeeD (SwinL, single-scale))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Panoptic SegmentationonCOCO minival
PQ· 2022-09-29
58.5
best: 61.2 (HyperSeg (Swin-B))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Panoptic SegmentationonCOCO minival
PQst· 2022-09-29
48.8
best: 49.2 (OneFormer (InternImage-H,single-scale))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Panoptic SegmentationonCOCO minival
PQth· 2022-09-29
64.9
best: 67.1 (OneFormer (InternImage-H,single-scale))
Dilated Neighborhood Attention Transformer arXiv:2209.15001

Medical5 results

Semantic SegmentationonCOCO minival
mIoU· 2022-09-29
68.3
best: 69.7 (UMG-CLIP-E/14)
SOTA
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Semantic SegmentationonCOCO minival
AP· 2022-09-29
49.2
best: 53.2 (OpenSeeD (SwinL, single-scale))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Semantic SegmentationonCOCO minival
PQ· 2022-09-29
58.5
best: 61.2 (HyperSeg (Swin-B))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Semantic SegmentationonCOCO minival
PQst· 2022-09-29
48.8
best: 49.2 (OneFormer (InternImage-H,single-scale))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
Semantic SegmentationonCOCO minival
PQth· 2022-09-29
64.9
best: 67.1 (OneFormer (InternImage-H,single-scale))
Dilated Neighborhood Attention Transformer arXiv:2209.15001

Audio5 results

10-shot image generationonCOCO minival
mIoU· 2022-09-29
68.3
best: 69.7 (UMG-CLIP-E/14)
SOTA
Dilated Neighborhood Attention Transformer arXiv:2209.15001
10-shot image generationonCOCO minival
AP· 2022-09-29
49.2
best: 53.2 (OpenSeeD (SwinL, single-scale))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
10-shot image generationonCOCO minival
PQ· 2022-09-29
58.5
best: 61.2 (HyperSeg (Swin-B))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
10-shot image generationonCOCO minival
PQst· 2022-09-29
48.8
best: 49.2 (OneFormer (InternImage-H,single-scale))
Dilated Neighborhood Attention Transformer arXiv:2209.15001
10-shot image generationonCOCO minival
PQth· 2022-09-29
64.9
best: 67.1 (OneFormer (InternImage-H,single-scale))
Dilated Neighborhood Attention Transformer arXiv:2209.15001