AI Paper Atlas

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

Demystifying Foreground-Background Memorization in Diffusion Models

Jimmy Z. Di, Yiwei Lu, Yaoliang Yu, Gautam Kamath, Adam Dziedzic, Franziska Boenisch

AAAI 2026 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 0 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
Aggregate neurons across a prompt cluster (NeMo-C) instead of per-prompt neuronsNeMo · 500 memorized promptsmitigation score: 0.74 -> 0.83Improved
NeMo-C vs NeMo on image qualityNeMo · Image qualityQ-Align: 3.63 -> 3.52Hurt
NeMo-C vs NeMo on image qualityNeMo · Image qualityDB-CNN: 0.587 -> 0.586No clear effect
Apply any model-level mitigation (NeMo, Wanda, DetectMem)Stable Diffusion v1.4 · Verbatim memorizationVM rateImproved
Apply any model-level mitigationStable Diffusion v1.4 · Foreground memorizationFM rateNo clear effect
Apply mitigation methodsStable Diffusion v1.4 · One-to-many correspondencematched training imagesNo clear effect
Use MS-SSIM instead of SSCD in FB-Mem (ablation)FB-Mem · TM vs NM classificationAUROC: 0.992 -> 0.962Hurt
Use MS-SSIM instead of SSIM for VM vs NM (ablation)FB-Mem · VM vs NM classificationaccuracy: 0.954 -> 0.997Improved

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