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/MKConv

MKConv

Reported on 11 benchmarks across 5 tasks · 1 paper

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

Medical4 results

  • Semantic SegmentationonS3DIS Area5
    mAcc· 2021-07-27
    75.1
    best: 81.6 (Sonata + PTv3)
    MKConv: Multidimensional Feature Representation for Point Cloud AnalysisarXiv:2107.12655
  • Semantic SegmentationonS3DIS Area5
    mIoU· 2021-07-27
    67.7
    best: 76 (Sonata + PTv3)
    MKConv: Multidimensional Feature Representation for Point Cloud AnalysisarXiv:2107.12655
  • Semantic SegmentationonS3DIS Area5
    oAcc· 2021-07-27
    89.6
    best: 93 (Sonata + PTv3)
    MKConv: Multidimensional Feature Representation for Point Cloud AnalysisarXiv:2107.12655
  • Semantic SegmentationonShapeNet-Part
    Instance Average IoU· 2021-07-27
    86.7
    best: 89.1 (GeomGCNN)
    MKConv: Multidimensional Feature Representation for Point Cloud AnalysisarXiv:2107.12655

Audio4 results

  • 10-shot image generationonS3DIS Area5
    mAcc· 2021-07-27
    75.1
    best: 81.6 (Sonata + PTv3)
    MKConv: Multidimensional Feature Representation for Point Cloud AnalysisarXiv:2107.12655
  • 10-shot image generationonS3DIS Area5
    mIoU· 2021-07-27
    67.7
    best: 76 (Sonata + PTv3)
    MKConv: Multidimensional Feature Representation for Point Cloud AnalysisarXiv:2107.12655
  • 10-shot image generationonS3DIS Area5
    oAcc· 2021-07-27
    89.6
    best: 93 (Sonata + PTv3)
    MKConv: Multidimensional Feature Representation for Point Cloud AnalysisarXiv:2107.12655
  • 10-shot image generationonShapeNet-Part
    Instance Average IoU· 2021-07-27
    86.7
    best: 89.1 (GeomGCNN)
    MKConv: Multidimensional Feature Representation for Point Cloud AnalysisarXiv:2107.12655

Computer Vision3 results

  • Shape Representation Of 3D Point CloudsonModelNet40
    Overall Accuracy· 2021-07-27
    94
    best: 95.3 (PointGST)
    MKConv: Multidimensional Feature Representation for Point Cloud AnalysisarXiv:2107.12655
  • 3D Point Cloud ClassificationonModelNet40
    Overall Accuracy· 2021-07-27
    94
    best: 95.3 (PointGST)
    MKConv: Multidimensional Feature Representation for Point Cloud AnalysisarXiv:2107.12655
  • 3D Point Cloud ReconstructiononModelNet40
    Overall Accuracy· 2021-07-27
    94
    best: 95.3 (PointGST)
    MKConv: Multidimensional Feature Representation for Point Cloud AnalysisarXiv:2107.12655