AI Paper Atlas

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

A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis

Aishwarya Agarwal, Srikrishna Karanam, K J Joseph, Apoorv Saxena, Koustava Goswami, Balaji Vasan Srinivasan

ICCV 2023 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 50 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 attention retention loss (ablation)Stable Diffusion · Animal-Object promptstext-text similarity: 0.78 -> 0.83Improved
add attention segregation loss (ablation)Stable Diffusion · Animal-Animal promptstext-text similarity: 0.76 -> 0.79Improved
add both segregation and retention losses (ablation)Stable Diffusion · Animal-Animal promptstext-text similarity: 0.76 -> 0.82Improved
add both losses (ablation)Stable Diffusion · Object-Object promptstext-text similarity: 0.77 -> 0.82Improved
A-STAR instead of Attend-and-Excite on top of Stable DiffusionStable Diffusion · Animal-Animal promptstext-text similarity: 0.80 -> 0.82Improved
A-STAR vs Stable Diffusion on CLIP similarityStable Diffusion · all three prompt categoriesCLIP full prompt / min object similarity: +7.1% and +10.8%Improved
Composable Diffusion instead of plain Stable DiffusionStable Diffusion · Animal-Animal promptstext-text similarity: 0.76 -> 0.69Hurt
use A-STAR vs baselines in a user studyStable Diffusion · User study, animal-animalpreference rate: 2.2% -> 94.8%Improved
apply losses to prompts where baseline already succeedsStable Diffusion · qualitative, easy promptssemantic faithfulnessNo clear effect

Later papers that compared with this method

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

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