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/DeepCut

DeepCut

Reported on 10 benchmarks across 6 tasks · 2 papers · 7 SOTA

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

Computer Vision8 results

  • Object LocalizationonCOCO_20k
    CorLoc· 2022-12-12
    61.6
    SOTA
    DeepCut: Unsupervised Segmentation using Graph Neural Networks ClusteringarXiv:2212.05853
  • Object LocalizationonPASCAL VOC 2012
    CorLoc· 2022-12-12
    72.2
    SOTA
    DeepCut: Unsupervised Segmentation using Graph Neural Networks ClusteringarXiv:2212.05853
  • Object LocalizationonPASCAL VOC 2007
    CorLoc· 2022-12-12
    69.8
    SOTA
    DeepCut: Unsupervised Segmentation using Graph Neural Networks ClusteringarXiv:2212.05853
  • Instance SegmentationonECSSD
    mIoU· 2022-12-12
    74.6
    best: 77.83 (UnSegArmaNet)
    SOTA
    DeepCut: Unsupervised Segmentation using Graph Neural Networks ClusteringarXiv:2212.05853
  • Instance SegmentationonDUTS
    mIoU· 2022-12-12
    59.5
    SOTA
    DeepCut: Unsupervised Segmentation using Graph Neural Networks ClusteringarXiv:2212.05853
  • Unsupervised Object SegmentationonECSSD
    mIoU· 2022-12-12
    74.6
    best: 77.83 (UnSegArmaNet)
    SOTA
    DeepCut: Unsupervised Segmentation using Graph Neural Networks ClusteringarXiv:2212.05853
  • Unsupervised Object SegmentationonDUTS
    mIoU· 2022-12-12
    59.5
    SOTA
    DeepCut: Unsupervised Segmentation using Graph Neural Networks ClusteringarXiv:2212.05853
  • Pose EstimationonMPII Human Pose
    PCKh-0.5· 2015-11-20
    82.4
    best: 94.3 (PCT (swin-l, test set))
    DeepCut: Joint Subset Partition and Labeling for Multi Person Pose EstimationarXiv:1511.06645

Methodology1 result

  • 3DonMPII Human Pose
    PCKh-0.5· 2015-11-20
    82.4
    best: 94.3 (PCT (swin-l, test set))
    DeepCut: Joint Subset Partition and Labeling for Multi Person Pose EstimationarXiv:1511.06645

Audio1 result

  • 1 Image, 2*2 StitchionMPII Human Pose
    PCKh-0.5· 2015-11-20
    82.4
    best: 94.3 (PCT (swin-l, test set))
    DeepCut: Joint Subset Partition and Labeling for Multi Person Pose EstimationarXiv:1511.06645