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/DiffSeg (512)

DiffSeg (512)

Reported on 8 benchmarks across 2 tasks · 1 paper · 6 SOTA

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

Medical4 results

  • Semantic SegmentationonCityscapes
    Pixel Accuracy· 2023-08-23
    76
    SOTA
    Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable DiffusionarXiv:2308.12469
  • Semantic SegmentationonCOCO-Stuff-27
    Pixel Accuracy· 2023-08-23
    72.5
    SOTA
    Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable DiffusionarXiv:2308.12469
  • Semantic SegmentationonCOCO-Stuff-27
    mIoU· 2023-08-23
    43.6
    SOTA
    Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable DiffusionarXiv:2308.12469
  • Semantic SegmentationonCityscapes
    mIoU· 2023-08-23
    21.2
    best: 77.8 (SPFNet34M)
    Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable DiffusionarXiv:2308.12469

Audio4 results

  • 10-shot image generationonCityscapes
    Pixel Accuracy· 2023-08-23
    76
    SOTA
    Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable DiffusionarXiv:2308.12469
  • 10-shot image generationonCOCO-Stuff-27
    Pixel Accuracy· 2023-08-23
    72.5
    SOTA
    Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable DiffusionarXiv:2308.12469
  • 10-shot image generationonCOCO-Stuff-27
    mIoU· 2023-08-23
    43.6
    SOTA
    Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable DiffusionarXiv:2308.12469
  • 10-shot image generationonCityscapes
    mIoU· 2023-08-23
    21.2
    best: 77.8 (SPFNet34M)
    Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable DiffusionarXiv:2308.12469