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/Axial-DeepLab-XL (Mapillary Vistas, multi-scale)

Axial-DeepLab-XL (Mapillary Vistas, multi-scale)

Reported on 12 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.

Medical4 results

Semantic SegmentationonCityscapes test
PQ· uses extra data· 2020-03-17
66.6
best: 68 (OneFormer (ConvNeXt-L, single-scale, Mapillary Vistas-Pretrained))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Semantic SegmentationonCityscapes val
AP· uses extra data· 2020-03-17
44.2
best: 50.6 (ViT-P (OneFormer, InternImage-H))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Semantic SegmentationonCityscapes val
PQ· uses extra data· 2020-03-17
68.5
best: 70.8 (ViT-P (OneFormer, InternImage-H))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Semantic SegmentationonCityscapes val
mIoU· uses extra data· 2020-03-17
84.6
best: 90.3 (EfficientPS (Cityscapes-fine))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853

Audio4 results

10-shot image generationonCityscapes test
PQ· uses extra data· 2020-03-17
66.6
best: 68 (OneFormer (ConvNeXt-L, single-scale, Mapillary Vistas-Pretrained))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
10-shot image generationonCityscapes val
AP· uses extra data· 2020-03-17
44.2
best: 50.6 (ViT-P (OneFormer, InternImage-H))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
10-shot image generationonCityscapes val
PQ· uses extra data· 2020-03-17
68.5
best: 70.8 (ViT-P (OneFormer, InternImage-H))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
10-shot image generationonCityscapes val
mIoU· uses extra data· 2020-03-17
84.6
best: 90.3 (EfficientPS (Cityscapes-fine))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853

Computer Vision4 results

Panoptic SegmentationonCityscapes test
PQ· uses extra data· 2020-03-17
66.6
best: 68 (OneFormer (ConvNeXt-L, single-scale, Mapillary Vistas-Pretrained))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Panoptic SegmentationonCityscapes val
AP· uses extra data· 2020-03-17
44.2
best: 50.6 (ViT-P (OneFormer, InternImage-H))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Panoptic SegmentationonCityscapes val
PQ· uses extra data· 2020-03-17
68.5
best: 70.8 (ViT-P (OneFormer, InternImage-H))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853
Panoptic SegmentationonCityscapes val
mIoU· uses extra data· 2020-03-17
84.6
best: 90.3 (EfficientPS (Cityscapes-fine))
SOTA
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation arXiv:2003.07853