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/CLIPSeg (ViT-B/16)

CLIPSeg (ViT-B/16)

Reported on 6 benchmarks across 1 task · 1 paper · 6 SOTA

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

Computer Vision18 results

  • Referring Image MattingonRefMatte
    MSE· 2021-12-18
    0.0064
    best: 0.0022 (CLIPMat (ViT-L/14))
    SOTA
    Image Segmentation Using Text and Image PromptsarXiv:2112.10003
  • Referring Image MattingonRefMatte
    MSE(E)· 2021-12-18
    0.0067
    best: 0.0023 (CLIPMat (ViT-L/14))
    SOTA
    Image Segmentation Using Text and Image PromptsarXiv:2112.10003
  • Referring Image MattingonRefMatte
    MAD· 2021-12-18
    0.1222
    SOTA
    Image Segmentation Using Text and Image PromptsarXiv:2112.10003
  • Referring Image MattingonRefMatte
    MAD(E)· 2021-12-18
    0.1282
    SOTA
    Image Segmentation Using Text and Image PromptsarXiv:2112.10003
  • Referring Image MattingonRefMatte
    SAD· 2021-12-18
    211.86
    SOTA
    Image Segmentation Using Text and Image PromptsarXiv:2112.10003
  • Referring Image MattingonRefMatte
    SAD(E)· 2021-12-18
    222.37
    SOTA
    Image Segmentation Using Text and Image PromptsarXiv:2112.10003
  • Referring Image MattingonRefMatte
    MAD· 2021-12-18
    0.0394
    best: 0.1222
    Image Segmentation Using Text and Image PromptsarXiv:2112.10003
  • Referring Image MattingonRefMatte
    MAD(E)· 2021-12-18
    0.0419
    best: 0.1282
    Image Segmentation Using Text and Image PromptsarXiv:2112.10003
  • Referring Image MattingonRefMatte
    MSE· 2021-12-18
    0.0358
    best: 0.0022 (CLIPMat (ViT-L/14))
    Image Segmentation Using Text and Image PromptsarXiv:2112.10003
  • Referring Image MattingonRefMatte
    MSE(E)· 2021-12-18
    0.0381
    best: 0.0023 (CLIPMat (ViT-L/14))
    Image Segmentation Using Text and Image PromptsarXiv:2112.10003
  • Referring Image MattingonRefMatte
    SAD· 2021-12-18
    69.13
    best: 211.86
    Image Segmentation Using Text and Image PromptsarXiv:2112.10003
  • Referring Image MattingonRefMatte
    SAD(E)· 2021-12-18
    73.53
    best: 222.37
    Image Segmentation Using Text and Image PromptsarXiv:2112.10003
  • Referring Image MattingonRefMatte
    MAD· 2021-12-18
    0.0101
    best: 0.1222
    Image Segmentation Using Text and Image PromptsarXiv:2112.10003
  • Referring Image MattingonRefMatte
    MAD(E)· 2021-12-18
    0.0106
    best: 0.1282
    Image Segmentation Using Text and Image PromptsarXiv:2112.10003
  • Referring Image MattingonRefMatte
    SAD· 2021-12-18
    17.75
    best: 211.86
    Image Segmentation Using Text and Image PromptsarXiv:2112.10003
  • Referring Image MattingonRefMatte
    SAD(E)· 2021-12-18
    18.69
    best: 222.37
    Image Segmentation Using Text and Image PromptsarXiv:2112.10003
  • Referring Image MattingonRefMatte
    MSE· 2021-12-18
    0.1178
    best: 0.0022 (CLIPMat (ViT-L/14))
    Image Segmentation Using Text and Image PromptsarXiv:2112.10003
  • Referring Image MattingonRefMatte
    MSE(E)· 2021-12-18
    0.1236
    best: 0.0023 (CLIPMat (ViT-L/14))
    Image Segmentation Using Text and Image PromptsarXiv:2112.10003