TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/TASCNet (ResNet-50)

TASCNet (ResNet-50)

Reported on 15 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.

Medical5 results

  • Semantic SegmentationonCityscapes val
    AP· uses extra data· 2018-12-04
    37.6
    best: 50.6 (ViT-P (OneFormer, InternImage-H))
    Learning to Fuse Things and StuffarXiv:1812.01192
  • Semantic SegmentationonCityscapes val
    PQ· uses extra data· 2018-12-04
    59.2
    best: 70.8 (ViT-P (OneFormer, InternImage-H))
    Learning to Fuse Things and StuffarXiv:1812.01192
  • Semantic SegmentationonCityscapes val
    PQst· uses extra data· 2018-12-04
    61.5
    best: 74.1 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
    Learning to Fuse Things and StuffarXiv:1812.01192
  • Semantic SegmentationonCityscapes val
    PQth· uses extra data· 2018-12-04
    56
    best: 64.6 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
    Learning to Fuse Things and StuffarXiv:1812.01192
  • Semantic SegmentationonCityscapes val
    mIoU· uses extra data· 2018-12-04
    77.8
    best: 90.3 (EfficientPS (Cityscapes-fine))
    Learning to Fuse Things and StuffarXiv:1812.01192

Audio5 results

  • 10-shot image generationonCityscapes val
    AP· uses extra data· 2018-12-04
    37.6
    best: 50.6 (ViT-P (OneFormer, InternImage-H))
    Learning to Fuse Things and StuffarXiv:1812.01192
  • 10-shot image generationonCityscapes val
    PQ· uses extra data· 2018-12-04
    59.2
    best: 70.8 (ViT-P (OneFormer, InternImage-H))
    Learning to Fuse Things and StuffarXiv:1812.01192
  • 10-shot image generationonCityscapes val
    PQst· uses extra data· 2018-12-04
    61.5
    best: 74.1 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
    Learning to Fuse Things and StuffarXiv:1812.01192
  • 10-shot image generationonCityscapes val
    PQth· uses extra data· 2018-12-04
    56
    best: 64.6 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
    Learning to Fuse Things and StuffarXiv:1812.01192
  • 10-shot image generationonCityscapes val
    mIoU· uses extra data· 2018-12-04
    77.8
    best: 90.3 (EfficientPS (Cityscapes-fine))
    Learning to Fuse Things and StuffarXiv:1812.01192

Computer Vision5 results

  • Panoptic SegmentationonCityscapes val
    AP· uses extra data· 2018-12-04
    37.6
    best: 50.6 (ViT-P (OneFormer, InternImage-H))
    Learning to Fuse Things and StuffarXiv:1812.01192
  • Panoptic SegmentationonCityscapes val
    PQ· uses extra data· 2018-12-04
    59.2
    best: 70.8 (ViT-P (OneFormer, InternImage-H))
    Learning to Fuse Things and StuffarXiv:1812.01192
  • Panoptic SegmentationonCityscapes val
    PQst· uses extra data· 2018-12-04
    61.5
    best: 74.1 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
    Learning to Fuse Things and StuffarXiv:1812.01192
  • Panoptic SegmentationonCityscapes val
    PQth· uses extra data· 2018-12-04
    56
    best: 64.6 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
    Learning to Fuse Things and StuffarXiv:1812.01192
  • Panoptic SegmentationonCityscapes val
    mIoU· uses extra data· 2018-12-04
    77.8
    best: 90.3 (EfficientPS (Cityscapes-fine))
    Learning to Fuse Things and StuffarXiv:1812.01192