atlas

Research map / Image generation / GANs

Adversarial Learning of Semantic Relevance in Text to Image Synthesis

AAAI 2019 · Image generation › GANs · approach: Large-scale GAN latent analysis · 58 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
Replace auxiliary class prediction with semantic relevance regressionText-SeGAN versus TAC-GAN · Oxford-102Inception score: 3.45$\pm$0.05 -> 3.65$\pm$0.06Helped
Use easy-to-hard negative sampling instead of hard negative sampling (ablation)Text-SeGAN · Oxford-102Inception score: 3.33$\pm$0.03 -> 4.03$\pm$0.07Helped
Use easy-to-hard negative sampling instead of semi-easy negative sampling (ablation)Text-SeGAN · Oxford-102Inception score: 3.69$\pm$0.04 -> 4.03$\pm$0.07Helped
Use easy-to-hard negative sampling instead of semi-hard negative sampling (ablation)Text-SeGAN · Oxford-102Inception score: 3.70$\pm$0.04 -> 4.03$\pm$0.07Helped
Use semi-hard rather than semi-easy negative sampling (ablation)Text-SeGAN · Oxford-102Inception score: 3.69$\pm$0.04 -> 3.70$\pm$0.04No clear effect
Use easy negative sampling (ablation)Text-SeGAN · Oxford-102Inception scoreNo clear effect

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