AI Paper Atlas

Research map / Image generation / GANs

CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and Reconstruction

Shengke Sun, Ziqian Luan, Zhanshan Zhao, Shijie Luo, Shuzhen Han

ECCV 2024 · Image generation › GANs · approach: Large-scale GAN latent analysis · 2 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 latent consistency and reconstruction losses (lambda1=5, lambda2=0.5)DCGAN · CIFAR-10FID: 38.56 -> 23.3Improved
Add latent consistency and reconstruction lossesStyleGAN-V2 · FFHQ 256FID: 3.86 -> 3.44Improved
Add both losses on top of StyleGAN-V2-ADAStyleGAN-V2-ADA · AFHQ-CatFID: 6.05 -> 4.45Improved
Use only the latent consistency loss (lambda2=0) instead of both losses (ablation)CLR-GAN · CIFAR-10FID: 23.3 -> 25.15Hurt
Use only the reconstruction loss (lambda1=0) instead of both losses (ablation)CLR-GAN · CIFAR-10FID: 23.3 -> 26.09Hurt
Add only one of the two losses on high-resolution data (ablation)StyleGAN-V2 · FFHQ 256FID: 3.86 -> 3.75 and 3.77No clear effect
Raise latent loss weight lambda1 from 5 to 15 (ablation)CLR-GAN · CIFAR-10FID: 25.20 -> 26.30Hurt
Raise reconstruction weight lambda2 from 0.5 to 5 at lambda1=5 (ablation)CLR-GAN · CIFAR-10FID: 23.3 -> 25.55Hurt
Use CLR-GAN instead of AdaptiveMix on CelebADCGAN · CelebA 64x64FID: 12.43 -> 13.63Hurt
Use the CLR-GAN trained discriminator as a feature extractor with a linear headDiscriminator · CIFAR-10 classificationaccuracy: 97.7% (HCGNet) vs 98.8%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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