AI Paper Atlas

Research map / Image generation / GANs

Spectral Regularization for Combating Mode Collapse in GANs

Kanglin Liu, Wenming Tang, Fei Zhou, Guoping Qiu

ICCV 2019 · Image generation › GANs · approach: Stabilized GAN training · 87 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 spectral regularization (compensating singular values) to spectral normalizationSN-GAN · ImageNet E2048-64Inception Score: 21.78 -> 31.58Improved
add spectral regularizationSN-GAN · ImageNet E512-64Inception Score: 34.13 -> 40.76Improved
add spectral regularizationSN-GAN · CIFAR-10 C64-32 (small discriminator)FID: 85.15 -> 56.11Improved
add spectral regularizationSN-GAN · CIFAR-10 A16-128FID: 22.31 -> 24.67Hurt
add spectral regularizationSN-GAN · all 26 settingsmode collapse: none happened to SR-GANs in all 10 settings where SN-GANs collapsedImproved
add spectral regularizationSN-GAN · average over settingsIS and FID: IS improved by 13.9% and FID by 21.8%Improved
resume SN-GAN snapshot at 40k iterations with dynamic-compensation SR (ablation)SN-GAN · ImageNet E2048-64IS and FID: IS improved by 44.9% and FID by 9.1%Improved
increase static compensation i from 0.25r to 0.5r (ablation)SR-GAN · groups A, D, EInception Score: 0.25N to 0.5N improvedImproved
increase static compensation i from 0.5r to r (ablation)SR-GAN · groups A, D, EInception Score: 0.5N to N deterioratedHurt
increase static compensation i (ablation)SR-GAN · group BInception Score: performance increases steadily with iImproved
dynamic instead of static compensation (ablation)SR-GAN · A128-128 and D128-256Inception Score: static betterHurt
dynamic instead of static compensation (ablation)SR-GAN · B16-64, C64-32, E512-64Inception Score: dynamic better in the rest tasksImproved

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