AI Paper Atlas

Research map / Image generation / GANs

Tempered Adversarial Networks

Mehdi S. M. Sajjadi, Giambattista Parascandolo, Arash Mehrjou, Bernhard Schölkopf

ICML 2018 · Image generation › GANs · approach: GAN latent optimization and evaluation · 2 citations (OpenAlex)

Read the paper

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 the scheduled lensDCGAN · MNISTFID: 42 vs. 22Improved
Add the scheduled lensDCGAN · Color MNISTFID: 53 vs. 8Improved
Add the scheduled lensLSGAN · MNISTFID: 19 -> 14Improved
Add the scheduled lensLSGAN · Color MNISTFID: 90 vs. 14 to 22Improved
Add the scheduled lensLSGAN · CelebAFID: 52 vs. 32 to 37Improved
Add the scheduled lensWGAN-GP · CIFAR-10FID: 39 vs. 39Mixed
Keep λ fixed at 1 instead of scheduling it down to 0 (ablation)DCGAN with lens · MNISTFID: 60 vs. 22Hurt
Schedule λ down to 0 rather than keeping it fixed at 1 (ablation)DCGAN with lens · MNISTconvergence speedImproved
Use a dynamic lens rather than no lensDCGAN · Color MNISTtraining stabilityImproved

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