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/MaskFormer (Swin-L)

MaskFormer (Swin-L)

Reported on 9 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.

Medical3 results

Semantic SegmentationonCOCO test-dev
PQ· 2021-07-13
53.3
best: 59.5 (Mask DINO (single scale))
Per-Pixel Classification is Not All You Need for Semantic Segmentation arXiv:2107.06278
Semantic SegmentationonCOCO test-dev
PQst· 2021-07-13
44.5
best: 58.9 (MaskConver (ResNet50, single-scale))
Per-Pixel Classification is Not All You Need for Semantic Segmentation arXiv:2107.06278
Semantic SegmentationonCOCO test-dev
PQth· 2021-07-13
59.1
best: 65.1 (Mask2Former (Swin-L))
Per-Pixel Classification is Not All You Need for Semantic Segmentation arXiv:2107.06278

Audio3 results

10-shot image generationonCOCO test-dev
PQ· 2021-07-13
53.3
best: 59.5 (Mask DINO (single scale))
Per-Pixel Classification is Not All You Need for Semantic Segmentation arXiv:2107.06278
10-shot image generationonCOCO test-dev
PQst· 2021-07-13
44.5
best: 58.9 (MaskConver (ResNet50, single-scale))
Per-Pixel Classification is Not All You Need for Semantic Segmentation arXiv:2107.06278
10-shot image generationonCOCO test-dev
PQth· 2021-07-13
59.1
best: 65.1 (Mask2Former (Swin-L))
Per-Pixel Classification is Not All You Need for Semantic Segmentation arXiv:2107.06278

Computer Vision3 results

Panoptic SegmentationonCOCO test-dev
PQ· 2021-07-13
53.3
best: 59.5 (Mask DINO (single scale))
Per-Pixel Classification is Not All You Need for Semantic Segmentation arXiv:2107.06278
Panoptic SegmentationonCOCO test-dev
PQst· 2021-07-13
44.5
best: 58.9 (MaskConver (ResNet50, single-scale))
Per-Pixel Classification is Not All You Need for Semantic Segmentation arXiv:2107.06278
Panoptic SegmentationonCOCO test-dev
PQth· 2021-07-13
59.1
best: 65.1 (Mask2Former (Swin-L))
Per-Pixel Classification is Not All You Need for Semantic Segmentation arXiv:2107.06278