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/BigGAN-deep

BigGAN-deep

Reported on 6 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.

Medical5 results

  • Image GenerationonImageNet 128x128
    FID· 2018-09-28
    5.7
    best: 1.26 (SiD2)
    SOTA
    Large Scale GAN Training for High Fidelity Natural Image SynthesisarXiv:1809.11096
  • Image GenerationonImageNet 128x128
    IS· 2018-09-28
    124.5
    best: 190.5 (VDM++)
    SOTA
    Large Scale GAN Training for High Fidelity Natural Image SynthesisarXiv:1809.11096
  • Image GenerationonImageNet 256x256
    FID· 2018-09-28
    8.1
    best: 1.06 (SiT-XL/2 + UCGM-S (E2E-VAE + 40 sampling steps + CFG))
    SOTA
    Large Scale GAN Training for High Fidelity Natural Image SynthesisarXiv:1809.11096
  • Image GenerationonImageNet 128x128
    Inception score· uses extra data· 2018-09-28
    124.5
    best: 262.85 (Omni-INR-GAN)
    SOTA
    Large Scale GAN Training for High Fidelity Natural Image SynthesisarXiv:1809.11096
  • Image GenerationonImageNet 128x128
    FID· uses extra data· 2018-09-28
    5.7
    best: 1.26 (SiD2)
    Large Scale GAN Training for High Fidelity Natural Image SynthesisarXiv:1809.11096

Computer Vision2 results

  • Conditional Image GenerationonImageNet 128x128
    FID· uses extra data· 2018-09-28
    5.7
    best: 2.19 (EluCD_DDPM)
    SOTA
    Large Scale GAN Training for High Fidelity Natural Image SynthesisarXiv:1809.11096
  • Conditional Image GenerationonImageNet 128x128
    Inception score· uses extra data· 2018-09-28
    124.5
    best: 262.85 (Omni-INR-GAN)
    SOTA
    Large Scale GAN Training for High Fidelity Natural Image SynthesisarXiv:1809.11096