AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Semantic Image Synthesis via Adversarial Learning

Hao Dong, Simiao Yu, Chao Wu, Yike Guo

ICCV 2017 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 275 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 the proposed adversarial encoder-decoder with residual transformation instead of the baselineBaseline · Caltech-200 birds poseaverage rank: 2.87 -> 1.61Improved
use the proposed model instead of the baselineBaseline · Caltech-200 birds backgroundaverage rank: 2.68 -> 1.93Improved
use the proposed model instead of the baselineBaseline · Caltech-200 birds text matchaverage rank: 2.11 -> 1.94Improved
use the proposed model instead of the baselineBaseline · Oxford-102 flowers shapeaverage rank: 2.97 -> 1.55Improved
use the proposed model instead of the baselineBaseline · Oxford-102 flowers backgroundaverage rank: 2.62 -> 1.74Improved
use the proposed model instead of the baselineBaseline · Oxford-102 flowers text matchaverage rank: 2.52 -> 1.75Improved
replace the learned encoder with a pretrained VGG encoder (ablation)Ours · Caltech-200 birds backgroundaverage rank: 1.93 -> 1.39Improved
replace the learned encoder with a pretrained VGG encoder (ablation)Ours · Caltech-200 birds poseaverage rank: 1.61 -> 1.52Improved
replace the learned encoder with a pretrained VGG encoder (ablation)Ours · Caltech-200 birds text matchaverage rank: 1.94 -> 1.95No clear effect
replace the learned encoder with a pretrained VGG encoder (ablation)Ours · Oxford-102 flowers backgroundaverage rank: 1.74 -> 1.64Improved
replace the learned encoder with a pretrained VGG encoder (ablation)Ours · Oxford-102 flowers text matchaverage rank: 1.75 -> 1.72No 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