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/COPS (ResNet-50)

COPS (ResNet-50)

Reported on 27 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.

Medical9 results

Semantic SegmentationonCityscapes test
PQ· 2021-06-06
60
best: 68 (OneFormer (ConvNeXt-L, single-scale, Mapillary Vistas-Pretrained))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
Semantic SegmentationonCityscapes val
AP· 2021-06-06
34.1
best: 50.6 (ViT-P (OneFormer, InternImage-H))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
Semantic SegmentationonCityscapes val
PQ· 2021-06-06
62.1
best: 70.8 (ViT-P (OneFormer, InternImage-H))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
Semantic SegmentationonCityscapes val
PQst· 2021-06-06
67.2
best: 74.1 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
Semantic SegmentationonCityscapes val
PQth· 2021-06-06
55.1
best: 64.6 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
Semantic SegmentationonCityscapes val
mIoU· 2021-06-06
79.3
best: 90.3 (EfficientPS (Cityscapes-fine))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
Semantic SegmentationonCOCO test-dev
PQ· 2021-06-06
38.5
best: 59.5 (Mask DINO (single scale))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
Semantic SegmentationonCOCO test-dev
PQst· 2021-06-06
34.8
best: 58.9 (MaskConver (ResNet50, single-scale))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
Semantic SegmentationonCOCO test-dev
PQth· 2021-06-06
41
best: 65.1 (Mask2Former (Swin-L))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188

Audio9 results

10-shot image generationonCityscapes test
PQ· 2021-06-06
60
best: 68 (OneFormer (ConvNeXt-L, single-scale, Mapillary Vistas-Pretrained))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
10-shot image generationonCityscapes val
AP· 2021-06-06
34.1
best: 50.6 (ViT-P (OneFormer, InternImage-H))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
10-shot image generationonCityscapes val
PQ· 2021-06-06
62.1
best: 70.8 (ViT-P (OneFormer, InternImage-H))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
10-shot image generationonCityscapes val
PQst· 2021-06-06
67.2
best: 74.1 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
10-shot image generationonCityscapes val
PQth· 2021-06-06
55.1
best: 64.6 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
10-shot image generationonCityscapes val
mIoU· 2021-06-06
79.3
best: 90.3 (EfficientPS (Cityscapes-fine))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
10-shot image generationonCOCO test-dev
PQ· 2021-06-06
38.5
best: 59.5 (Mask DINO (single scale))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
10-shot image generationonCOCO test-dev
PQst· 2021-06-06
34.8
best: 58.9 (MaskConver (ResNet50, single-scale))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
10-shot image generationonCOCO test-dev
PQth· 2021-06-06
41
best: 65.1 (Mask2Former (Swin-L))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188

Computer Vision9 results

Panoptic SegmentationonCityscapes test
PQ· 2021-06-06
60
best: 68 (OneFormer (ConvNeXt-L, single-scale, Mapillary Vistas-Pretrained))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
Panoptic SegmentationonCityscapes val
AP· 2021-06-06
34.1
best: 50.6 (ViT-P (OneFormer, InternImage-H))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
Panoptic SegmentationonCityscapes val
PQ· 2021-06-06
62.1
best: 70.8 (ViT-P (OneFormer, InternImage-H))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
Panoptic SegmentationonCityscapes val
PQst· 2021-06-06
67.2
best: 74.1 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
Panoptic SegmentationonCityscapes val
PQth· 2021-06-06
55.1
best: 64.6 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
Panoptic SegmentationonCityscapes val
mIoU· 2021-06-06
79.3
best: 90.3 (EfficientPS (Cityscapes-fine))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
Panoptic SegmentationonCOCO test-dev
PQ· 2021-06-06
38.5
best: 59.5 (Mask DINO (single scale))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
Panoptic SegmentationonCOCO test-dev
PQst· 2021-06-06
34.8
best: 58.9 (MaskConver (ResNet50, single-scale))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188
Panoptic SegmentationonCOCO test-dev
PQth· 2021-06-06
41
best: 65.1 (Mask2Former (Swin-L))
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach arXiv:2106.03188