AI Paper Atlas

Research map / Image generation / GANs

A Framework of Composite Functional Gradient Methods for Generative Adversarial Models

Rie Johnson, Tong Zhang

TPAMI 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
use xICFG instead of best baseline GAN/WGANgpconvolutional generators · MNISTinception score: 9.57 -> 9.78Improved
use xICFG instead of best baseline GAN/WGANgpconvolutional generators · SVHNinception score: 8.33 -> 8.72Improved
use xICFG instead of best baselinefully-connected generators · SVHNinception score: 7.81 -> 8.16Improved
use xICFG instead of best baselineResNet generators · LSUN BR+LR (64x64)inception score: 1.56 -> 1.64Improved
use xICFG instead of best baselineconvolutional generators · LSUN T+B (64x64)inception score: 1.76 -> 1.80Mixed
reduce number of ICFG iterations T from 25 to 5 (SVHN), 10 (MNIST), 15 (LSUN) (ablation)xICFG · MNIST, SVHN, LSUNinception scoreNo clear effect
use final approximator as generator instead of the full composite generator (ablation)xICFG · MNIST, SVHN, LSUNinception scoreHurt
remove batch normalization from all methods (ablation)convolutional generators · image generationinception scoreNo clear effect

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