PeerGAN

Reported on 4 benchmarks across 1 task · 1 paper

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

Medical4 results

Image GenerationonFashion-MNIST
FID· 2021-01-19
21.73
best: 10.3 (GLF+perceptual loss (ours))
DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Training arXiv:2101.07524
Image GenerationonSTL-10
FID· 2021-01-19
51.37
best: 6.91 (Diffusion ProjectedGAN)
DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Training arXiv:2101.07524
Image GenerationonCelebA 64x64
FID· 2021-01-19
13.95
best: 1.27 (DDPM-IP)
DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Training arXiv:2101.07524
Image GenerationonCIFAR-10
FID· 2021-01-19
21.55
best: 1.22 (GMem)
DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Training arXiv:2101.07524