AI Paper Atlas

Research map / Image generation / GANs

Omni-GAN: On the Secrets of cGANs and Beyond

Peng Zhou, Lingxi Xie, Bingbing Ni, Cong Geng, Qi Tian

ICCV 2021 · Image generation › GANs · approach: Conditional GANs · 17 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add weight decay to Omni-GAN (ablation)Omni-GAN · CIFAR100FID: 26.51 -> 8.41Improved
add weight decay to AC-GAN (ablation)AC-GAN · CIFAR100FID: 34.19 -> 16.41Improved
add weight decay to projection-based BigGAN (ablation)BigGAN · CIFAR100FID: 10.12 -> 13.73Hurt
add differentiable augmentation to BigGAN (ablation)BigGAN · CIFAR100FID: 10.12 -> 8.63Improved
add DiffAug to AC-GAN without weight decay (ablation)AC-GAN · CIFAR100FID: 34.19 -> 38.01No clear effect
add DiffAug to Omni-GAN with weight decay (ablation)Omni-GAN · CIFAR100FID and IS: 8.41 -> 11.39 FID; 13.30 -> 15.37 ISMixed
replace AC-GAN loss with the improved loss (ImAC-GAN)AC-GAN with weight decay · CIFAR100FID: 16.41 -> 8.11Improved
add implicit neural representation to Omni-GAN generator (ablation)Omni-GAN with weight decay · CIFAR100FID: 8.41 -> 7.63Improved
add DiffAug to Omni-INR-GAN with weight decay (ablation)Omni-INR-GAN · CIFAR10FID: 5.25 -> 4.32Improved
use Omni-GAN instead of BigGANBigGAN · ImageNet 128x128IS: 104.57 -> 190.94Improved
add INR to Omni-GAN generator output (ablation)Omni-GAN · ImageNet 128x128IS: 190.94 -> 262.85Improved
use Omni-GAN instead of BigGANBigGAN · ImageNet 256x256IS: 187.60 -> 304.05Improved

Later papers that compared with this method

2 later accepted papers report OmniGAN as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy