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/PPT+SparseUNet

PPT+SparseUNet

Reported on 7 benchmarks across 4 tasks · 1 paper · 3 SOTA

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

Computer Vision3 results

  • 3D Semantic SegmentationonScanNet200
    test mIoU· uses extra data· 2023-08-18
    33.2
    best: 44.9 (DITR)
    SOTA
    Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt TrainingarXiv:2308.09718
  • 3D Semantic SegmentationonScanNet200
    val mIoU· uses extra data· 2023-08-18
    31.9
    best: 41.2 (DITR)
    Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt TrainingarXiv:2308.09718
  • LIDAR Semantic SegmentationonnuScenes
    val mIoU· uses extra data· 2023-08-18
    0.786
    best: 0.842 (DITR)
    Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt TrainingarXiv:2308.09718

Medical2 results

  • Semantic SegmentationonScanNet200
    test mIoU· uses extra data· 2023-08-18
    33.2
    best: 44.9 (DITR)
    SOTA
    Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt TrainingarXiv:2308.09718
  • Semantic SegmentationonScanNet200
    val mIoU· uses extra data· 2023-08-18
    31.9
    best: 41.2 (DITR)
    Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt TrainingarXiv:2308.09718

Audio2 results

  • 10-shot image generationonScanNet200
    test mIoU· uses extra data· 2023-08-18
    33.2
    best: 44.9 (DITR)
    SOTA
    Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt TrainingarXiv:2308.09718
  • 10-shot image generationonScanNet200
    val mIoU· uses extra data· 2023-08-18
    31.9
    best: 41.2 (DITR)
    Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt TrainingarXiv:2308.09718