AI Paper Atlas

Research map / Image generation / GANs

Modular Generative Adversarial Networks

Bo Zhao, Bo Chang, Zequn Jie, Leonid Sigal

ECCV 2018 · Image generation › GANs · approach: Large-scale GAN latent analysis · 80 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 mask prediction in transformer module (ablation)ModularGAN · CelebA hair+smile+genderclassification error (%): 56.08 -> 6.09Improved
add mask prediction in transformer module (ablation)ModularGAN · CelebA hair+smileclassification error (%): 30.85 -> 4.03Improved
add mask prediction in transformer module (ablation)ModularGAN · CelebA gender (single)classification error (%): 3.58 -> 2.61Improved
add mask prediction in transformer module (ablation)ModularGAN · CelebA hair color (single)classification error (%): 4.01 -> 3.86Improved
add cyclic loss (ablation)ModularGAN · CelebA hair+smile+genderclassification error (%): 52.87 -> 6.09Improved
add cyclic loss (ablation)ModularGAN · CelebA hair+smileclassification error (%): 25.34 -> 4.03Improved
add cyclic loss (ablation)ModularGAN · CelebA hair color (single)classification error (%): 3.93 -> 3.86No clear effect
add cyclic loss (ablation)ModularGAN · CelebA gender (single)classification error (%): 2.87 -> 2.61Improved
fixed instead of random order of transformer modules (ablation)ModularGAN · CelebA hair+smile+genderclassification error (%): 6.23 -> 6.09No clear effect
fixed instead of random order of transformer modules (ablation)ModularGAN · CelebA hair+genderclassification error (%): 5.98 -> 6.51Mixed
fixed instead of random order of transformer modules (ablation)ModularGAN · CelebA hair+smileclassification error (%): 4.37 -> 4.03No clear effect
use modular transformers instead of one single multi-domain generator (StarGAN)multi-attribute translation · CelebA hair+smile+genderclassification error (%): 7.63 -> 6.09Improved

Earlier methods this paper compares with

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