AI Paper Atlas

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

Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking

Kaiyuan Deng, Bo Hui, Gen Li, Jie Ji, Minghai Qin, Geng Yuan, Xiaolong Ma

ICML 2026 · Image generation › Text-to-image diffusion · approach: Concept erasure in diffusion models · 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
use FIA masking instead of fine-tuning-based unlearning (ESD, SalUn, SPM, MACE)SD v1.5 · Imagenette 10-class unlearningavg forgetting accuracy (%): 1.9 vs 38.58 (ESD), 23.17 (SalUn), 78.22 (MACE)Improved
use FIA instead of fine-tuning methods in terms of image qualitySD v1.5 · MS COCO-30K CLIP after 10-class unlearningCLIP score: 29.56 vs 31.05 (MACE), 31.42 (SD v1.5)Hurt
use FIA instead of training-free CPSD v1.5 · Imagenette 10-class unlearningCLIP score: 27.93 -> 29.56Improved
use FIA instead of CP for preservationSD v1.5 · Imagenette forget 5 / preserve 5preserving accuracy (%): 52.4 -> 76.7Improved
use FIA instead of UCESD v1.5 · Imagenette forget 5 / preserve 5overall score (%): 81.7 -> 86.0Improved
increase number of forgotten classes (forget X / preserve 10-X) (ablation)FIA · Imagenetteforgetting accuracyNo clear effect
apply FIA to SD v1.4 for explicit contentSD v1.4 · I2P NudeNettotal detections: 743 -> 32Improved
apply FIA to SD v1.4SD v1.4 · MS COCO-30KFID: 14.04 -> 14.02No clear effect
apply FIA to forget five artist stylesSD v1.5 · Five artist stylesCLIPa: 42.10 -> 27.45Improved
apply FIA to forget five artist stylesSD v1.5 · MS COCO-30KFID: 14.5 -> 16.7Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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