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/HALO

HALO

Reported on 6 benchmarks across 4 tasks · 1 paper · 3 SOTA

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

Methodology4 results

  • Domain AdaptationonSYNTHIA-to-Cityscapes
    mIoU· 2023-06-19
    78.1
    SOTA
    Hyperbolic Active Learning for Semantic Segmentation under Domain ShiftarXiv:2306.11180
  • Domain AdaptationonGTA5 to Cityscapes
    mIoU· uses extra data· 2023-06-19
    77.8
    SOTA
    Hyperbolic Active Learning for Semantic Segmentation under Domain ShiftarXiv:2306.11180
  • Domain AdaptationonCityscapes to ACDC
    mIoU· 2023-06-19
    71.9
    best: 78.8 (SoRA)
    Hyperbolic Active Learning for Semantic Segmentation under Domain ShiftarXiv:2306.11180
  • Domain AdaptationonGTA5 to Cityscapes
    mIoU· 2023-06-19
    73.3
    best: 77.8
    Hyperbolic Active Learning for Semantic Segmentation under Domain ShiftarXiv:2306.11180

Computer Vision1 result

  • Source-Free Domain AdaptationonGTA5 to Cityscapes
    mIoU· 2023-06-19
    73.3
    SOTA
    Hyperbolic Active Learning for Semantic Segmentation under Domain ShiftarXiv:2306.11180

Medical1 result

  • Semantic SegmentationonCityscapes val
    mIoU· 2023-06-19
    77.8
    best: 90.3 (EfficientPS (Cityscapes-fine))
    Hyperbolic Active Learning for Semantic Segmentation under Domain ShiftarXiv:2306.11180

Audio1 result

  • 10-shot image generationonCityscapes val
    mIoU· 2023-06-19
    77.8
    best: 90.3 (EfficientPS (Cityscapes-fine))
    Hyperbolic Active Learning for Semantic Segmentation under Domain ShiftarXiv:2306.11180