AI Paper Atlas

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

Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model Unlearning

Saemi Moon, Minjong Lee, Sangdon Park, Dongwoo Kim

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Concept erasure in diffusion models · 13 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
unlearn with RECELERSD v1.5 · HUB overalltarget proportion: 0.649 -> 0.086Improved
unlearn with SASD v1.5 · HUB overallFID: 13.203 -> 32.572Hurt
unlearn with UCESD v1.5 · HUB NSFWtarget proportion: 0.647 -> 0.603No clear effect
unlearn with UCESD v1.5 · HUB overallImageReward: 0.172 -> 0.193Improved
unlearn with MACESD v1.5 · HUB NSFWImageReward: 0.172 -> -1.403Hurt
unlearn with RECELERSD v1.5 · HUB overallmultilingual robustness (target proportion): 0.489 -> 0.030Improved
unlearn with ACSD v1.5 · HUB overalltarget proportion: 0.649 -> 0.301Mixed
use HUB NSFW prompts instead of I2P promptsoriginal SD v1.5 · NSFWtarget proportion: 0.339 -> 0.647Improved
unlearn with UCESD v1.5 · HUB NSFWattack robustness: 0.796 -> 0.780No 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