AI Paper Atlas

Research map / Image generation / GANs

Logo Synthesis and Manipulation With Clustered Generative Adversarial Networks

Alexander Sage, Eirikur Agustsson, Radu Timofte, Luc Van Gool

CVPR 2018 · Image generation › GANs · approach: Large-scale GAN latent analysis · 47 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
Use auxiliary-classifier conditioning with 32 ResNet-feature clusters instead of unconditional iWGANiWGAN · CIFAR-10Inception score: 7.853$\pm$0.072 -> 8.673$\pm$0.075Improved
Use layer conditioning with 32 ResNet-feature clusters instead of unconditional iWGANiWGAN · CIFAR-10Inception score: 7.853$\pm$0.072 -> 7.831$\pm$0.072No clear effect
Use ResNet-feature clustering rather than autoencoder clustering with AC conditioning and 32 clustersiWGAN-AC · CIFAR-10Inception score: 7.885$\pm$0.083 -> 8.673$\pm$0.075Improved
Use auxiliary-classifier conditioning rather than layer conditioning with 32 ResNet-feature clustersiWGAN with RC clustering · CIFAR-10Inception score: 7.831$\pm$0.072 -> 8.673$\pm$0.075Improved
Increase ResNet-feature cluster count from 10 to 32 with AC conditioning (ablation)iWGAN-AC · CIFAR-10Inception score: 8.433$\pm$0.068 -> 8.673$\pm$0.075Improved
Increase ResNet-feature cluster count from 32 to 128 with AC conditioning (ablation)iWGAN-AC · CIFAR-10Inception score: 8.673$\pm$0.075 -> 8.625$\pm$0.109No clear effect
Increase ResNet-feature cluster count from 32 to 128 with AC conditioning (ablation)iWGAN-AC · CIFAR-10MS-SSIM: 0.0500$\pm$0.0016 -> 0.0465$\pm$0.0015Improved
Use layer conditioning with 16 ResNet-feature clusters rather than unconditional iWGANiWGAN · LLD-icon-sharpCORNIA score: 54.27$\pm$0.67 -> 55.37$\pm$0.67Hurt
Use layer conditioning with 128 ResNet-feature clusters rather than unconditional iWGANiWGAN · LLD-icon-sharpCORNIA score: 54.27$\pm$0.67 -> 55.27$\pm$0.68Hurt
Use layer conditioning with 100 autoencoder clusters rather than DCGAN-LCGAN on LLD-icon · LLD-iconCORNIA score: 62.12$\pm$0.51 -> 60.24$\pm$0.61Improved
Add the latent-space and cluster-label directional shifts together rather than applying just one space's shift (ablation)iWGAN-LC logo manipulation · LLD-logovisual attribute shift qualityImproved

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