atlas

Research map / Image generation / GANs

Generative Adversarial Text to Image Synthesis

ICML 2016 · Image generation › GANs · approach: Large-scale GAN latent analysis · 2,214 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 text-embedding interpolation regularization (ablation)Text-conditional GAN · CUB zero-shotvisual plausibilityHelped
Add text-embedding interpolation regularization (ablation)Text-conditional GAN · CUB zero-shotreliability of plausible image generationHelped
Use matching-aware discrimination with real images paired to mismatched text (ablation)Text-conditional GAN · CUBvisual plausibilityNo clear effect
Remove both matching-aware discrimination and interpolation regularization (ablation)Text-conditional GAN · Oxford-102 Flowersvisual plausibilityNo clear effect
Use matching-aware discrimination and interpolation regularization together (ablation)Text-conditional GAN · CUB style verificationAU-ROCHelped
Use GAN-CLS rather than AlignDRAWText-to-image synthesis · MS COCOsample sharpness and resolutionHelped
Use AlignDRAW rather than GAN-CLSText-to-image synthesis · MS COCOsensitivity to single-word changesHelped

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