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/ SemiVL, ViT-B/16)

SemiOVS (w/ SemiVL, ViT-B/16)

Reported on 10 benchmarks across 2 tasks

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

Medical5 results

  • Semantic SegmentationonPASCAL VOC 2012 92 labeled
    Validation mIoU· uses extra data
    87
  • Semantic SegmentationonPASCAL VOC 2012 732 labeled
    Validation mIoU· uses extra data
    87.9
    best: 90 (UniMatch V2 (DINOv2-B))
  • Semantic SegmentationonPASCAL VOC 2012 1464 labels
    Validation mIoU· uses extra data
    88
    best: 90.8 (UniMatch V2 (DINOv2-B))
  • Semantic SegmentationonPASCAL VOC 2012 366 labeled
    Validation mIoU· uses extra data
    87.5
    best: 88.9 (UniMatch V2 (DINOv2-B))
  • Semantic SegmentationonPASCAL VOC 2012 183 labeled
    Validation mIoU· uses extra data
    87.3
    best: 87.9 (UniMatch V2 (DINOv2-B))

Audio5 results

  • 10-shot image generationonPASCAL VOC 2012 92 labeled
    Validation mIoU· uses extra data
    87
  • 10-shot image generationonPASCAL VOC 2012 732 labeled
    Validation mIoU· uses extra data
    87.9
    best: 90 (UniMatch V2 (DINOv2-B))
  • 10-shot image generationonPASCAL VOC 2012 1464 labels
    Validation mIoU· uses extra data
    88
    best: 90.8 (UniMatch V2 (DINOv2-B))
  • 10-shot image generationonPASCAL VOC 2012 366 labeled
    Validation mIoU· uses extra data
    87.5
    best: 88.9 (UniMatch V2 (DINOv2-B))
  • 10-shot image generationonPASCAL VOC 2012 183 labeled
    Validation mIoU· uses extra data
    87.3
    best: 87.9 (UniMatch V2 (DINOv2-B))