AI Paper Atlas

Research map / Image generation / GANs

RoCGAN: Robust Conditional GAN

Grigorios G. Chrysos, Jean Kossaifi, Stefanos P. Zafeiriou

IJCV 2020 · Image generation › GANs · approach: Stabilized GAN training · 75 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 autoencoder pathway with shared decoder (RoCGAN) to cGAN4layer cGAN · Natural scenes denoising 25%SSIM: 0.628 -> 0.668Improved
add autoencoder pathway with shared decoder (RoCGAN) to cGAN4layer cGAN · Faces denoising 25%SSIM: 0.803 -> 0.834Improved
add autoencoder pathway under extra test noise4layer cGAN · Faces denoising 35% (extra noise)SSIM: 0.765 -> 0.821Improved
add autoencoder pathway on sparse inpainting4layer cGAN · Faces sparse inpainting 50%SSIM: 0.801 -> 0.804No clear effect
add autoencoder pathway under extra inpainting corruption4layer cGAN · Natural scenes sparse inpainting 75%SSIM: 0.542 -> 0.548No clear effect
add autoencoder pathway on ImageNet4layer cGAN · ImageNet denoising 25%SSIM: 0.657 -> 0.679Improved
add autoencoder pathway to 5layer network5layer cGAN · Faces sparse inpainting 75%SSIM: 0.707 -> 0.818Improved
add autoencoder pathway to 4layer-skip network4layer-skip cGAN · Faces sparse inpainting 50%SSIM: 0.855 -> 0.859No clear effect
use 6layer instead of 5layer RoCGANRoCGAN · Faces denoising 25%SSIM: 0.890 -> 0.881No clear effect
train with additional unlabelled data for AE pathwayRoCGAN · Faces sparse inpainting 75% (50k labelled)SSIM: 0.617 -> 0.681Improved
use OneNet instead of the cGAN baselinecGAN · Faces denoising 25%SSIM: 0.803 -> 0.758Hurt

Later papers that compared with this method

1 later accepted paper reports RoCGAN as a baseline in their results tables; 1 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