AI Paper Atlas

Research map / Image generation / GANs

Unsupervised Image Generation With Infinite Generative Adversarial Networks

Hui Ying, He Wang, Tianjia Shao, Yin Yang, Kun Zhou

ICCV 2021 · Image generation › GANs · approach: GAN latent optimization and evaluation · 8 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 K>1 modes (MIC-GANs) instead of single GAN (K=1) (ablation)StyleGAN2 · Hybrid (StyleGAN2)FID: 15.47 -> 11.2Improved
use K>1 modes instead of K=1 (ablation)DCGAN · Hybrid (DCGAN)FID: 60.83 -> 45.07Improved
use K=15 modes instead of K=1 (ablation)StyleGAN2 · MNISTFID: 12.96 -> 9.92Improved
use K=15 modes instead of K=1 (ablation)StyleGAN2 · HybridFID: 15.47 -> 15.7No clear effect
vary K among 15, 20, 25 (ablation)DCGAN · MNISTpurity: 0.9384, 0.9578, 0.93No clear effect
add MIC-GANs mode mixture to StyleGAN2-AdaStyleGAN2-Ada · CIFAR-10 (10 classes)FID: 5.03 -> 4.72Improved
add MIC-GANs mode mixture to StyleGAN2-AdaStyleGAN2-Ada · CIFAR-10 (4 classes)FID: 5.64 -> 5.31Improved
use MIC-GANs instead of Self-Conditioned GANSelf-Conditioned GAN · CIFAR-10 (4 classes)FID: 237.96 -> 5.31Improved
use MIC-GANs instead of DMGANDMGAN · MNISTpurity: 0.7612 -> 0.9489Improved
use MIC-GANs instead of DMGANDMGAN · HybridFID: 32.31 -> 11.2Improved
use MIC-GANs instead of ClusterGAN (given ground-truth K)ClusterGAN · MNISTFID: 9.27 -> 12.79Hurt
use MIC-GANs instead of ClusterGANClusterGAN · Hybridpurity: 0.9457 -> 0.9567Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

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