AI Paper Atlas

Research map / Image generation / GANs

Adversarial Feedback Loop

Firas Shama, Roey Mechrez, Alon Shoshan, Lihi Zelnik-Manor

ICCV 2019 · Image generation › GANs · approach: Stabilized GAN training · 28 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 AFL feedback modulesESRGAN · PIRM test set (x4 SR)Perceptual Index: 2.433 -> 2.135Improved
add AFL feedback modulesESRGAN · PIRM test set (x4 SR)RMSE: 16.34 -> 14.72Improved
add AFL with alpha=0.5DCGAN · CelebA (64x64)FID: 24.17 -> 17.32Improved
add AFL to WGAN-GPWGAN-GP · CIFAR-10Inception Score: 6.68 -> 7.07Improved
use real discriminator feedback instead of random normal input (ablation)WGAN-GP+AFL · CIFAR-10Inception Score: 3.44 -> 7.07Improved
use feedback of the correct image instead of a different image (ablation)WGAN-GP+AFL · CIFAR-10Inception Score: 5.76 -> 7.07Improved
vary feedback strength alpha from 0 to higher values (ablation)DCGAN+AFL · CelebA (64x64)FID: 24.17 -> 17.32Improved
use dual-input feedback modules instead of single-input (ablation)SN-GAN+AFL · CIFAR-10Inception ScoreImproved
replace feedback image with another reference image (feedback switching)DCGAN+AFL on CIFAR-10 · CIFAR-10Inception ScoreHurt

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