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/SemiOVS (w/ UniMatch, ResNet-101)

SemiOVS (w/ UniMatch, ResNet-101)

Reported on 16 benchmarks across 2 tasks

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

Medical8 results

  • Semantic SegmentationonPascal VOC 2012 6.25% labeled
    Validation mIoU· uses extra data
    81.5
    best: 82 (SemiOVS (w/ PrevMatch, ResNet-101))
  • Semantic SegmentationonPASCAL VOC 2012 92 labeled
    Validation mIoU· uses extra data
    80.4
    best: 87 (SemiOVS (w/ SemiVL, ViT-B/16))
  • Semantic SegmentationonPASCAL VOC 2012 732 labeled
    Validation mIoU· uses extra data
    81.7
    best: 90 (UniMatch V2 (DINOv2-B))
  • Semantic SegmentationonPASCAL VOC 2012 1464 labels
    Validation mIoU· uses extra data
    81.8
    best: 90.8 (UniMatch V2 (DINOv2-B))
  • Semantic SegmentationonPASCAL VOC 2012 25% labeled
    Validation mIoU· uses extra data
    81
    best: 81.3 (SemiOVS (w/ PrevMatch, ResNet-101))
  • Semantic SegmentationonPascal VOC 2012 12.5% labeled
    Validation mIoU· uses extra data
    82.4
  • Semantic SegmentationonPASCAL VOC 2012 366 labeled
    Validation mIoU· uses extra data
    81.6
    best: 88.9 (UniMatch V2 (DINOv2-B))
  • Semantic SegmentationonPASCAL VOC 2012 183 labeled
    Validation mIoU· uses extra data
    81.3
    best: 87.9 (UniMatch V2 (DINOv2-B))

Audio8 results

  • 10-shot image generationonPascal VOC 2012 6.25% labeled
    Validation mIoU· uses extra data
    81.5
    best: 82 (SemiOVS (w/ PrevMatch, ResNet-101))
  • 10-shot image generationonPASCAL VOC 2012 92 labeled
    Validation mIoU· uses extra data
    80.4
    best: 87 (SemiOVS (w/ SemiVL, ViT-B/16))
  • 10-shot image generationonPASCAL VOC 2012 732 labeled
    Validation mIoU· uses extra data
    81.7
    best: 90 (UniMatch V2 (DINOv2-B))
  • 10-shot image generationonPASCAL VOC 2012 1464 labels
    Validation mIoU· uses extra data
    81.8
    best: 90.8 (UniMatch V2 (DINOv2-B))
  • 10-shot image generationonPASCAL VOC 2012 25% labeled
    Validation mIoU· uses extra data
    81
    best: 81.3 (SemiOVS (w/ PrevMatch, ResNet-101))
  • 10-shot image generationonPascal VOC 2012 12.5% labeled
    Validation mIoU· uses extra data
    82.4
  • 10-shot image generationonPASCAL VOC 2012 366 labeled
    Validation mIoU· uses extra data
    81.6
    best: 88.9 (UniMatch V2 (DINOv2-B))
  • 10-shot image generationonPASCAL VOC 2012 183 labeled
    Validation mIoU· uses extra data
    81.3
    best: 87.9 (UniMatch V2 (DINOv2-B))