AI Paper Atlas

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

Subject-driven Text-to-Image Generation via Apprenticeship Learning

Wenhu Chen, Hexiang Hu, YANDONG LI, Nataniel Ruiz, Xuhui Jia, Ming-Wei Chang, William W. Cohen

NeurIPS 2023 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 44 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 Delta CLIP score filtering of expert-generated data (ablation)SuTI · DreamBench-v2overall human score: 0.54 -> 0.82Improved
further fine-tune SuTI on subject images for 500 steps (Dream-SuTI) (ablation)SuTI · DreamBench-v2overall human score: 0.82 -> 0.87Improved
increase number of in-context demonstrations (ablation)SuTI · DreamBench-v2human scoreImproved
use apprentice SuTI instead of DreamBooth per-subject tuning (Imagen)DreamBooth · DreamBenchDINO: 0.696 -> 0.741Improved
use SuTI instead of DreamBoothDreamBooth · DreamBenchCLIP-T: 0.306 -> 0.304No clear effect
use SuTI instead of DreamBoothDreamBooth · DreamBench-v2overall human score: 0.77 -> 0.82Improved
use SuTI instead of DreamBoothDreamBooth · DreamBench-v2photorealism: 0.98 -> 0.92Hurt
use SuTI instead of Re-ImagenRe-Imagen · DreamBench-v2overall human score: 0.42 -> 0.82Improved

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