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/StyleSwin

StyleSwin

Reported on 7 benchmarks across 1 task · 1 paper · 3 SOTA

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

Medical7 results

  • Image GenerationonCelebA-HQ 1024x1024
    FID· 2021-12-20
    4.43
    SOTA
    StyleSwin: Transformer-based GAN for High-resolution Image GenerationarXiv:2112.10762
  • Image GenerationonCelebA 256x256
    FID· 2021-12-20
    3.25
    SOTA
    StyleSwin: Transformer-based GAN for High-resolution Image GenerationarXiv:2112.10762
  • Image GenerationonCelebA-HQ 256x256
    FID· 2021-12-20
    3.25
    best: 3.15 (RDM)
    SOTA
    StyleSwin: Transformer-based GAN for High-resolution Image GenerationarXiv:2112.10762
  • Image GenerationonFFHQ
    FID· 2021-12-20
    5.07
    best: 2.77 (Anycost GAN)
    StyleSwin: Transformer-based GAN for High-resolution Image GenerationarXiv:2112.10762
  • Image GenerationonFFHQ 256 x 256
    FID· 2021-12-20
    2.81
    best: 1.68 (StyleSAN-XL)
    StyleSwin: Transformer-based GAN for High-resolution Image GenerationarXiv:2112.10762
  • Image GenerationonFFHQ 1024 x 1024
    FID· 2021-12-20
    5.07
    best: 1.61 (StyleSAN-XL)
    StyleSwin: Transformer-based GAN for High-resolution Image GenerationarXiv:2112.10762
  • Image GenerationonLSUN Churches 256 x 256
    FID· 2021-12-20
    2.95
    best: 1.59 (Projected GAN)
    StyleSwin: Transformer-based GAN for High-resolution Image GenerationarXiv:2112.10762