AI Paper Atlas

Research map / Image generation / GANs

Inducing Optimal Attribute Representations for Conditional GANs

Binod Bhattarai, Tae-Kyun Kim

ECCV 2020 · Image generation › GANs · approach: Conditional GANs · 25 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
switch conditioning from target (Std) to target-minus-source (Diff) one-hot (ablation)StarGAN · CelebA TARR avgTARR (%): 67.2% -> 74.5%Improved
replace one-hot with GCN-induced attribute representations (ablation)StarGAN (Diff) · CelebA TARR avgTARR (%): 74.5 -> 79.4Improved
add MTL at discriminator to gcn-reprs (ablation)StarGAN · CelebA TARR avgTARR (%): 79.4 -> 81.0Improved
train GCN and GAN end-to-end instead of multi-stage (ablation)StarGAN + gcn-reprs + MTL · CelebA TARR avgTARR (%): 81.0 -> 83.4Improved
add MTL at discriminator (13 attributes) (ablation)StarGAN one-hot Std · CelebA TARR avgTARR (%): 67.2 -> 68.3Improved
replace one-hot with latent-reprs (ablation)StarGAN (Diff) · CelebA TARR avgTARR (%): 74.5 -> 71.4Hurt
replace one-hot with attrbs-weights (ablation)StarGAN (Diff) · CelebA TARR avgTARR (%): 74.5 -> 76.0Improved
replace one-hot with co-occurrence vectors (ablation)StarGAN (Diff, 5 attributes) · CelebA TARR avg (5 attributes)TARR (%): 80.2 -> 78.6Hurt
replace one-hot with word2vec (ablation)StarGAN (Diff, 5 attributes) · CelebA TARR avg (5 attributes)TARR (%): 80.2 -> 81.3Improved
replace one-hot with gcn-reprs (ablation)StarGAN (Diff, 5 attributes) · CelebA TARR avg (5 attributes)TARR (%): 80.2 -> 84.0Improved
apply gcn-reprs + MTL + End2EndSTGAN · CelebA TARR avgTARR (%): 86.1 -> 89.1Improved
apply gcn-reprs + MTL + End2EndAttGAN · CelebA TARR avgTARR (%): 83 -> 90.3Improved

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