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/DiffusionSTR

DiffusionSTR

Reported on 18 benchmarks across 3 tasks · 1 paper

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

Computer Vision12 results

  • Scene ParsingonSVT
    Accuracy· 2023-06-29
    93.6
    best: 99.1 (CLIP4STR-H (DFN-5B))
    DiffusionSTR: Diffusion Model for Scene Text RecognitionarXiv:2306.16707
  • Scene ParsingonSVTP
    Accuracy· 2023-06-29
    89.2
    best: 98.6 (DTrOCR 105M)
    DiffusionSTR: Diffusion Model for Scene Text RecognitionarXiv:2306.16707
  • Scene ParsingonCUTE80
    Accuracy· 2023-06-29
    92.5
    best: 99.7 (CPPD)
    DiffusionSTR: Diffusion Model for Scene Text RecognitionarXiv:2306.16707
  • Scene ParsingonICDAR2015
    Accuracy· 2023-06-29
    86
    best: 93.5 (DTrOCR 105M)
    DiffusionSTR: Diffusion Model for Scene Text RecognitionarXiv:2306.16707
  • Scene ParsingonIIIT5k
    Accuracy· 2023-06-29
    97.3
    best: 99.6 (CLIP4STR-L (DataComp-1B))
    DiffusionSTR: Diffusion Model for Scene Text RecognitionarXiv:2306.16707
  • Scene ParsingonICDAR2013
    Accuracy· 2023-06-29
    97.1
    best: 99.42 (CLIP4STR-L*)
    DiffusionSTR: Diffusion Model for Scene Text RecognitionarXiv:2306.16707
  • Scene Text RecognitiononSVT
    Accuracy· 2023-06-29
    93.6
    best: 99.1 (CLIP4STR-H (DFN-5B))
    DiffusionSTR: Diffusion Model for Scene Text RecognitionarXiv:2306.16707
  • Scene Text RecognitiononSVTP
    Accuracy· 2023-06-29
    89.2
    best: 98.6 (DTrOCR 105M)
    DiffusionSTR: Diffusion Model for Scene Text RecognitionarXiv:2306.16707
  • Scene Text RecognitiononCUTE80
    Accuracy· 2023-06-29
    92.5
    best: 99.7 (CPPD)
    DiffusionSTR: Diffusion Model for Scene Text RecognitionarXiv:2306.16707
  • Scene Text RecognitiononICDAR2015
    Accuracy· 2023-06-29
    86
    best: 93.5 (DTrOCR 105M)
    DiffusionSTR: Diffusion Model for Scene Text RecognitionarXiv:2306.16707
  • Scene Text RecognitiononIIIT5k
    Accuracy· 2023-06-29
    97.3
    best: 99.6 (CLIP4STR-L (DataComp-1B))
    DiffusionSTR: Diffusion Model for Scene Text RecognitionarXiv:2306.16707
  • Scene Text RecognitiononICDAR2013
    Accuracy· 2023-06-29
    97.1
    best: 99.42 (CLIP4STR-L*)
    DiffusionSTR: Diffusion Model for Scene Text RecognitionarXiv:2306.16707

Audio6 results

  • 2D Semantic SegmentationonSVT
    Accuracy· 2023-06-29
    93.6
    best: 99.1 (CLIP4STR-H (DFN-5B))
    DiffusionSTR: Diffusion Model for Scene Text RecognitionarXiv:2306.16707
  • 2D Semantic SegmentationonSVTP
    Accuracy· 2023-06-29
    89.2
    best: 98.6 (DTrOCR 105M)
    DiffusionSTR: Diffusion Model for Scene Text RecognitionarXiv:2306.16707
  • 2D Semantic SegmentationonCUTE80
    Accuracy· 2023-06-29
    92.5
    best: 99.7 (CPPD)
    DiffusionSTR: Diffusion Model for Scene Text RecognitionarXiv:2306.16707
  • 2D Semantic SegmentationonICDAR2015
    Accuracy· 2023-06-29
    86
    best: 93.5 (DTrOCR 105M)
    DiffusionSTR: Diffusion Model for Scene Text RecognitionarXiv:2306.16707
  • 2D Semantic SegmentationonIIIT5k
    Accuracy· 2023-06-29
    97.3
    best: 99.6 (CLIP4STR-L (DataComp-1B))
    DiffusionSTR: Diffusion Model for Scene Text RecognitionarXiv:2306.16707
  • 2D Semantic SegmentationonICDAR2013
    Accuracy· 2023-06-29
    97.1
    best: 99.42 (CLIP4STR-L*)
    DiffusionSTR: Diffusion Model for Scene Text RecognitionarXiv:2306.16707