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/Panoptic FCN* (ResNet-FPN)

Panoptic FCN* (ResNet-FPN)

Reported on 12 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.

Medical4 results

Semantic SegmentationonCityscapes val
PQ· 2020-12-01
61.4
best: 70.8 (ViT-P (OneFormer, InternImage-H))
Fully Convolutional Networks for Panoptic Segmentation arXiv:2012.00720
Semantic SegmentationonCityscapes val
PQth· 2020-12-01
54.8
best: 64.6 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
Fully Convolutional Networks for Panoptic Segmentation arXiv:2012.00720
Semantic SegmentationonMapillary val
PQ· 2020-12-01
36.9
best: 46.7 (OneFormer (DiNAT-L, single-scale))
Fully Convolutional Networks for Panoptic Segmentation arXiv:2012.00720
Semantic SegmentationonMapillary val
PQth· 2020-12-01
32.9
best: 40.8 (Panoptic FCN* (Swin-L, single-scale))
Fully Convolutional Networks for Panoptic Segmentation arXiv:2012.00720

Audio4 results

10-shot image generationonCityscapes val
PQ· 2020-12-01
61.4
best: 70.8 (ViT-P (OneFormer, InternImage-H))
Fully Convolutional Networks for Panoptic Segmentation arXiv:2012.00720
10-shot image generationonCityscapes val
PQth· 2020-12-01
54.8
best: 64.6 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
Fully Convolutional Networks for Panoptic Segmentation arXiv:2012.00720
10-shot image generationonMapillary val
PQ· 2020-12-01
36.9
best: 46.7 (OneFormer (DiNAT-L, single-scale))
Fully Convolutional Networks for Panoptic Segmentation arXiv:2012.00720
10-shot image generationonMapillary val
PQth· 2020-12-01
32.9
best: 40.8 (Panoptic FCN* (Swin-L, single-scale))
Fully Convolutional Networks for Panoptic Segmentation arXiv:2012.00720

Computer Vision4 results

Panoptic SegmentationonCityscapes val
PQ· 2020-12-01
61.4
best: 70.8 (ViT-P (OneFormer, InternImage-H))
Fully Convolutional Networks for Panoptic Segmentation arXiv:2012.00720
Panoptic SegmentationonCityscapes val
PQth· 2020-12-01
54.8
best: 64.6 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
Fully Convolutional Networks for Panoptic Segmentation arXiv:2012.00720
Panoptic SegmentationonMapillary val
PQ· 2020-12-01
36.9
best: 46.7 (OneFormer (DiNAT-L, single-scale))
Fully Convolutional Networks for Panoptic Segmentation arXiv:2012.00720
Panoptic SegmentationonMapillary val
PQth· 2020-12-01
32.9
best: 40.8 (Panoptic FCN* (Swin-L, single-scale))
Fully Convolutional Networks for Panoptic Segmentation arXiv:2012.00720