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/OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained)

OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained)

Reported on 15 benchmarks across 3 tasks · 1 paper · 12 SOTA

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

Medical5 results

Semantic SegmentationonCityscapes val
AP· uses extra data· 2022-11-10
48.7
best: 50.6 (ViT-P (OneFormer, InternImage-H))
SOTA
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220
Semantic SegmentationonCityscapes val
PQ· uses extra data· 2022-11-10
70.1
best: 70.8 (ViT-P (OneFormer, InternImage-H))
SOTA
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220
Semantic SegmentationonCityscapes val
PQst· uses extra data· 2022-11-10
74.1
SOTA
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220
Semantic SegmentationonCityscapes val
PQth· uses extra data· 2022-11-10
64.6
SOTA
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220
Semantic SegmentationonCityscapes val
mIoU· uses extra data· 2022-11-10
84.6
best: 90.3 (EfficientPS (Cityscapes-fine))
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220

Audio5 results

10-shot image generationonCityscapes val
AP· uses extra data· 2022-11-10
48.7
best: 50.6 (ViT-P (OneFormer, InternImage-H))
SOTA
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220
10-shot image generationonCityscapes val
PQ· uses extra data· 2022-11-10
70.1
best: 70.8 (ViT-P (OneFormer, InternImage-H))
SOTA
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220
10-shot image generationonCityscapes val
PQst· uses extra data· 2022-11-10
74.1
SOTA
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220
10-shot image generationonCityscapes val
PQth· uses extra data· 2022-11-10
64.6
SOTA
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220
10-shot image generationonCityscapes val
mIoU· uses extra data· 2022-11-10
84.6
best: 90.3 (EfficientPS (Cityscapes-fine))
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220

Computer Vision5 results

Panoptic SegmentationonCityscapes val
AP· uses extra data· 2022-11-10
48.7
best: 50.6 (ViT-P (OneFormer, InternImage-H))
SOTA
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220
Panoptic SegmentationonCityscapes val
PQ· uses extra data· 2022-11-10
70.1
best: 70.8 (ViT-P (OneFormer, InternImage-H))
SOTA
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220
Panoptic SegmentationonCityscapes val
PQst· uses extra data· 2022-11-10
74.1
SOTA
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220
Panoptic SegmentationonCityscapes val
PQth· uses extra data· 2022-11-10
64.6
SOTA
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220
Panoptic SegmentationonCityscapes val
mIoU· uses extra data· 2022-11-10
84.6
best: 90.3 (EfficientPS (Cityscapes-fine))
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220