AI Paper Atlas

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

DAE-GAN: Dynamic Aspect-Aware GAN for Text-to-Image Synthesis

Shulan Ruan, Yong Zhang, Kun Zhang, Yanbo Fan, Fan Tang, Qi Liu, Enhong Chen

ICCV 2021 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 137 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
add Attended Global Refinement (AGR) (ablation)DAE-GAN · COCOFID: 149.79 -> 28.12Improved
add Attended Global Refinement (AGR) (ablation)DAE-GAN · COCOInception Score: 2.93 -> 35.08Improved
add Attended Global Refinement (AGR) (ablation)DAE-GAN · COCOR-precision: 2.34 -> 92.61Improved
add Aspect-aware Local Refinement (ALR) (ablation)DAE-GAN · COCOFID: 32.93 -> 28.12Improved
add Aspect-aware Local Refinement (ALR) (ablation)DAE-GAN · COCOInception Score: 31.07 -> 35.08Improved
add Aspect-aware Local Refinement (ALR) (ablation)DAE-GAN · COCOR-precision: 90.24 -> 92.61Improved
add aspect information to AGR (ablation)DAE-GAN · COCOFID: 28.60 -> 28.12Improved
add aspect information to AGR (ablation)DAE-GAN · COCOInception Score: 34.70 -> 35.08Improved
add aspect information to AGR (ablation)DAE-GAN · COCOR-precision: 92.28 -> 92.61Improved
DAE-GAN versus strongest prior method on ISDAE-GAN · CUB-200Inception Score: 5.23 vs 4.42Hurt
DAE-GAN versus best prior FIDDAE-GAN · CUB-200FID: 16.09 -> 15.19Improved
DAE-GAN versus best prior R-precisionDAE-GAN · CUB-200R-precision (%): 72.31 -> 85.45Improved

Later papers that compared with this method

1 later accepted paper reports DAE-GAN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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