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/MaskContrast (Saliency)

MaskContrast (Saliency)

Reported on 6 benchmarks across 3 tasks · 1 paper · 6 SOTA

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

Medical2 results

  • Semantic SegmentationonPASCAL VOC 2012 val
    Clustering [mIoU]· uses extra data· 2021-02-11
    44.2
    best: 53.4 (CAUSE (iBOT, ViT-B/16))
    SOTA
    Unsupervised Semantic Segmentation by Contrasting Object Mask ProposalsarXiv:2102.06191
  • Semantic SegmentationonPASCAL VOC 2012 val
    Linear Classifier [mIoU]· uses extra data· 2021-02-11
    63.9
    best: 75.7 (HCL (ViT-S/8))
    SOTA
    Unsupervised Semantic Segmentation by Contrasting Object Mask ProposalsarXiv:2102.06191

Computer Vision2 results

  • Unsupervised Semantic SegmentationonPASCAL VOC 2012 val
    Clustering [mIoU]· uses extra data· 2021-02-11
    44.2
    best: 53.4 (CAUSE (iBOT, ViT-B/16))
    SOTA
    Unsupervised Semantic Segmentation by Contrasting Object Mask ProposalsarXiv:2102.06191
  • Unsupervised Semantic SegmentationonPASCAL VOC 2012 val
    Linear Classifier [mIoU]· uses extra data· 2021-02-11
    63.9
    best: 75.7 (HCL (ViT-S/8))
    SOTA
    Unsupervised Semantic Segmentation by Contrasting Object Mask ProposalsarXiv:2102.06191

Audio2 results

  • 10-shot image generationonPASCAL VOC 2012 val
    Clustering [mIoU]· uses extra data· 2021-02-11
    44.2
    best: 53.4 (CAUSE (iBOT, ViT-B/16))
    SOTA
    Unsupervised Semantic Segmentation by Contrasting Object Mask ProposalsarXiv:2102.06191
  • 10-shot image generationonPASCAL VOC 2012 val
    Linear Classifier [mIoU]· uses extra data· 2021-02-11
    63.9
    best: 75.7 (HCL (ViT-S/8))
    SOTA
    Unsupervised Semantic Segmentation by Contrasting Object Mask ProposalsarXiv:2102.06191