AI Paper Atlas

Research map / Image generation / GANs

Exploring Gradient-Based Multi-directional Controls in GANs

Zikun Chen, Ruowei Jiang, Brendan Duke, Han Zhao, Parham Aarabi

ECCV 2022 · Image generation › GANs · approach: Large-scale GAN latent analysis · 19 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 gradient-based channel exclusion (top-k salient dimensions of entangled attributes) (ablation)gradient direction for gender · FFHQ StyleGAN2 (gender edit)entanglement with smile, eyeglasses, age (qualitative)Improved
exclude top-k channels with k set to 100 for all attributes (ablation)gradient direction · FFHQ StyleGAN2disentanglement (qualitative)Improved
tune k per attribute in {50,100,150,200,250} on 30-example meta-validation set (ablation)channel exclusion · FFHQ StyleGAN2disentanglement (qualitative)Improved
use gradient directions instead of InterFaceGAN SVM directions, genderInterFaceGAN · FFHQ StyleGAN2 gendermanipulation accuracy: 0.5859 -> 0.6937Improved
use gradient directions instead of InterFaceGAN, smileInterFaceGAN · FFHQ StyleGAN2 smilemanipulation accuracy: 0.9033 -> 0.9254Improved
use gradient directions instead of InterFaceGAN, eyeglassesInterFaceGAN · FFHQ StyleGAN2 eyeglassesmanipulation accuracy: 0.5946 -> 0.6626Improved
use gradient directions instead of InterFaceGAN, ageInterFaceGAN · FFHQ StyleGAN2 agemanipulation accuracy: 0.5620 -> 0.6139Improved
use gradient directions instead of StyleSpace, ageStyleSpace · FFHQ StyleGAN2 agemanipulation accuracy: 0.0034 -> 0.6139Improved
use gradient directions instead of StyleSpace, eyeglassesStyleSpace · FFHQ StyleGAN2 eyeglassesattribute dependency (mean AD)Hurt
use gradient directions instead of InterFaceGAN for gender and age as step growsInterFaceGAN · FFHQ StyleGAN2attribute dependency (mean AD)Improved
use gradient directions instead of StyleSpace/GANSpace for smileStyleSpace and GANSpace · FFHQ StyleGAN2 smileattribute dependency (mean AD)No clear effect

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