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/AUNet (ResNet-101-FPN)

AUNet (ResNet-101-FPN)

Reported on 24 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.

Medical8 results

Semantic SegmentationonCityscapes val
AP· 2018-12-10
34.4
best: 50.6 (ViT-P (OneFormer, InternImage-H))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
Semantic SegmentationonCityscapes val
PQ· 2018-12-10
59
best: 70.8 (ViT-P (OneFormer, InternImage-H))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
Semantic SegmentationonCityscapes val
PQst· 2018-12-10
62.1
best: 74.1 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
Semantic SegmentationonCityscapes val
PQth· 2018-12-10
54.8
best: 64.6 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
Semantic SegmentationonCityscapes val
mIoU· 2018-12-10
75.6
best: 90.3 (EfficientPS (Cityscapes-fine))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
Semantic SegmentationonCOCO test-dev
PQ· 2018-12-10
45.2
best: 59.5 (Mask DINO (single scale))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
Semantic SegmentationonCOCO test-dev
PQst· 2018-12-10
31.3
best: 58.9 (MaskConver (ResNet50, single-scale))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
Semantic SegmentationonCOCO test-dev
PQth· 2018-12-10
54.4
best: 65.1 (Mask2Former (Swin-L))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904

Audio8 results

10-shot image generationonCityscapes val
AP· 2018-12-10
34.4
best: 50.6 (ViT-P (OneFormer, InternImage-H))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
10-shot image generationonCityscapes val
PQ· 2018-12-10
59
best: 70.8 (ViT-P (OneFormer, InternImage-H))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
10-shot image generationonCityscapes val
PQst· 2018-12-10
62.1
best: 74.1 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
10-shot image generationonCityscapes val
PQth· 2018-12-10
54.8
best: 64.6 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
10-shot image generationonCityscapes val
mIoU· 2018-12-10
75.6
best: 90.3 (EfficientPS (Cityscapes-fine))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
10-shot image generationonCOCO test-dev
PQ· 2018-12-10
45.2
best: 59.5 (Mask DINO (single scale))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
10-shot image generationonCOCO test-dev
PQst· 2018-12-10
31.3
best: 58.9 (MaskConver (ResNet50, single-scale))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
10-shot image generationonCOCO test-dev
PQth· 2018-12-10
54.4
best: 65.1 (Mask2Former (Swin-L))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904

Computer Vision8 results

Panoptic SegmentationonCityscapes val
AP· 2018-12-10
34.4
best: 50.6 (ViT-P (OneFormer, InternImage-H))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
Panoptic SegmentationonCityscapes val
PQ· 2018-12-10
59
best: 70.8 (ViT-P (OneFormer, InternImage-H))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
Panoptic SegmentationonCityscapes val
PQst· 2018-12-10
62.1
best: 74.1 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
Panoptic SegmentationonCityscapes val
PQth· 2018-12-10
54.8
best: 64.6 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
Panoptic SegmentationonCityscapes val
mIoU· 2018-12-10
75.6
best: 90.3 (EfficientPS (Cityscapes-fine))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
Panoptic SegmentationonCOCO test-dev
PQ· 2018-12-10
45.2
best: 59.5 (Mask DINO (single scale))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
Panoptic SegmentationonCOCO test-dev
PQst· 2018-12-10
31.3
best: 58.9 (MaskConver (ResNet50, single-scale))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904
Panoptic SegmentationonCOCO test-dev
PQth· 2018-12-10
54.4
best: 65.1 (Mask2Former (Swin-L))
Attention-guided Unified Network for Panoptic Segmentation arXiv:1812.03904