Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/MSGAN

MSGAN

Reported on 9 benchmarks across 3 tasks · 2 papers · 1 SOTA

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

Medical5 results

Image GenerationonImageNet 32x32
FID· 2019-11-16
12.3
best: 0.79 (PaGoDA)
SOTA
Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Game arXiv:1911.06997
Image GenerationonCIFAR-100
FID· 2019-11-16
19.74
best: 2.99 (LeCAM (StyleGAN2 + ADA))
Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Game arXiv:1911.06997
Image GenerationonCIFAR-10
FID· 2019-03-13
28.73
best: 1.22 (GMem)
Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis arXiv:1903.05628
Image GenerationonCelebA-HQ
FID· 2019-03-13
33.1
best: 4.86 (MAT)
Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis arXiv:1903.05628
Image GenerationonAFHQ
FID· 2019-03-13
61.4
best: 16.2 (StarGAN v2)
Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis arXiv:1903.05628

Computer Vision2 results

Image-to-Image TranslationonCelebA-HQ
FID· 2019-03-13
33.1
best: 13.73 (StarGAN v2)
Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis arXiv:1903.05628
Image-to-Image TranslationonAFHQ
FID· 2019-03-13
61.4
best: 16.2 (StarGAN v2)
Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis arXiv:1903.05628

Miscellaneous2 results

1 Image, 2*2 StitchingonCelebA-HQ
FID· 2019-03-13
33.1
best: 13.73 (StarGAN v2)
Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis arXiv:1903.05628
1 Image, 2*2 StitchingonAFHQ
FID· 2019-03-13
61.4
best: 16.2 (StarGAN v2)
Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis arXiv:1903.05628