AI Paper Atlas

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

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models

Kien Nguyen, Anh Tran, Cuong Pham

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Concept erasure in diffusion models · 2 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 reference subspace from TI step 50 instead of step 70 (ablation)SuMa · Subclass erasureASR: 0.56 -> 0.12Improved
use reference subspace from TI step 50 instead of step 30 (ablation)SuMa · Subclass erasureFID: 19.11 -> 18.33Improved
use TI early-step token instead of general term as reference (ablation)SuMa · Subclass erasureASR: 0.18 -> 0.12Improved
use TI early-step token instead of general term as reference (ablation)SuMa · Identity erasureASR: 0.17 -> 0.09Improved
add subspace regularization (ablation)SuMa · Subclass erasureFID: 19.21 -> 18.33Improved
add subspace regularization (ablation)SuMa · Identity erasureFID: 20.31 -> 17.94Improved
add subspace regularization (ablation)SuMa · Instance erasureFID: 24.57 -> 22.34Improved
add subspace regularization (ablation)SuMa · Instance erasureCCE ASR: 0.15 -> 0.17Hurt
use CA loss as base method instead of UCE (ablation)SuMa · Identity erasure (Elon Musk)CCE ASR: 0.49 -> 0.07Improved
use CA loss as base method instead of ESD (ablation)SuMa · Instance erasure (Grumpy Cat)FID: 24.57 -> 22.34Improved
apply L_sub alone without L_CA (ablation)SuMa · Identity erasure (Elon Musk)ASR: 0.09 -> 0.73Hurt
apply L_sub alone without L_CA (ablation)SuMa · Artistic erasure (Van Gogh)ASR: 0.05 -> 0.76Hurt

Later papers that compared with this method

1 later accepted paper reports SUMA as a baseline in their results tables; 0 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