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/DiscoBox (ResNet-101-DCN-FPN)

DiscoBox (ResNet-101-DCN-FPN)

Reported on 6 benchmarks across 1 task · 1 paper

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

Computer Vision6 results

  • Weakly-supervised instance segmentationonCOCO test-dev
    AP· 2021-05-13
    35.8
    best: 37.9 (DiscoBox (ResNeXt-101-DCN-FPN))
    DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box SupervisionarXiv:2105.06464
  • Weakly-supervised instance segmentationonCOCO test-dev
    AP@50· 2021-05-13
    59.8
    best: 61.4 (DiscoBox (ResNeXt-101-DCN-FPN))
    DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box SupervisionarXiv:2105.06464
  • Weakly-supervised instance segmentationonCOCO test-dev
    AP@75· 2021-05-13
    36.4
    best: 40 (DiscoBox (ResNeXt-101-DCN-FPN))
    DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box SupervisionarXiv:2105.06464
  • Weakly-supervised instance segmentationonCOCO test-dev
    AP@L· 2021-05-13
    52.1
    best: 53.9 (DiscoBox (ResNeXt-101-DCN-FPN))
    DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box SupervisionarXiv:2105.06464
  • Weakly-supervised instance segmentationonCOCO test-dev
    AP@M· 2021-05-13
    38.7
    best: 41.1 (DiscoBox (ResNeXt-101-DCN-FPN))
    DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box SupervisionarXiv:2105.06464
  • Weakly-supervised instance segmentationonCOCO test-dev
    AP@S· 2021-05-13
    16.9
    best: 18 (DiscoBox (ResNeXt-101-DCN-FPN))
    DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box SupervisionarXiv:2105.06464