AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

How does Lipschitz Regularization Influence GAN Training?

Yipeng Qin, Niloy Mitra, Peter Wonka

ECCV 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Loss landscape analysis · 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
shrink domain with domain scaling alpha=1e-9 at k_SN=50 (ablation)NS-GAN-SN · CelebAFID: 242.64 -> 7.05Improved
shrink domain with domain scaling alpha=1e-9 at k_SN=50 (ablation)COS-GAN-SN · CelebAFID: 318.53 -> 6.31Improved
shrink domain with alpha=1e-25 at k_SN=50 instead of no scaling (ablation)EXP-GAN-SN · CIFAR10FID: 401.24 -> 21.91Improved
use alpha=1e-25 domain scaling so loss functions match WGAN-SN (ablation)NS-GAN-SN · CIFAR10FID: 23.36 -> 21.92Improved
lower k_SN from 1.0 to 0.2 (ablation)NS-GAN-SN · CelebAFID: 6.11 -> 18.59Hurt
raise k_SN from 1.0 to 50.0 (ablation)COS-GAN-SN · CIFAR10FID: 15.88 -> 370.13Hurt
raise k_SN from 1.0 to 50.0 (ablation)WGAN-SN · CIFAR10FID: 21.75 -> 23.36No clear effect
use WGAN loss instead of NS loss at k_SN=1.0WGAN-SN · CIFAR10FID: 15.81 -> 21.75Hurt
use non-standard cosine loss instead of NS loss at k_SN=1.0COS-GAN-SN · CelebAFID: 6.11 -> 5.20No clear effect
use zero-centered LS-GAN# instead of LS-GAN with domain scalingLS-GAN#-SN · CelebA (k_SN=50, alpha=1e-11)FID: 135.17 -> 6.66Improved
reduce k_SN from 5.0 to 0.25 restricts domain of NS-GAN loss (ablation)NS-GAN-SN · CelebA domaindomain width of discriminator output: [-8.130, 126.501] -> [-0.006, 0.006]Improved
enlarge domain with alpha=1e5 at k_SN=1.0 (ablation)LS-GAN-SN · MNISTFID: 23.37 -> 260.05Hurt

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