AI Paper Atlas

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

CGCE: Classifier-Guided Concept Erasure in Generative Models

Viet Nguyen, Vishal Patel

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Concept erasure in diffusion models · 3 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 token importance weighting s to the gradient refinement (ablation)CGCE · Nudity removal, I2P (SD-v1.4)ASR (%): 6.98 -> 4.62Improved
add token importance weighting s to the gradient refinement (ablation)CGCE · Nudity removal, UDA (SD-v1.4)ASR (%): 40.14 -> 27.46Improved
add token importance weighting s to the gradient refinement (ablation)CGCE · Nudity removal, COCOFID: 16.67 -> 16.10Improved
raise detection threshold tau from 0.50 to 0.75 (ablation)CGCE · Nudity removal, UDA (SD-v1.4)ASR (%): 27.46 -> 28.87No clear effect
lower detection threshold tau from 0.50 to 0.25 (ablation)CGCE · Nudity removal, SixCD (SD-v1.4)ASR (%): 2.47 -> 2.28No clear effect
increase step size eta from 1.0 to 1.5 (ablation)CGCE · Nudity removal (SD-v1.4)ASR and generative qualityMixed
use CGCE instead of SAFREE (token-level projection)SAFREE · Nudity removal, RAB (SD-v1.4)ASR (%): 74.74 -> 3.87Improved
use CGCE instead of SAFREE on FLUX with implicit story promptsSAFREE · Long implicit story prompts, FLUXASR (%): 67.00 -> 8.00Improved
apply CGCE to the base model on FLUX story promptsFLUX · Long implicit story prompts, FLUXASR (%): 78.00 -> 8.00Improved
apply three concept classifiers jointlyFLUX · Multi-concept (nudity, Van Gogh, church)ASR (%): 77.00 -> 15.00Improved
apply CGCE to multi-artist erasure (100 styles)SD-v1.4 · 100 artistic stylesCLIP_d: 5.99 -> 6.75Improved
use CGCE instead of fine-tuning (ESD) for training costESD · Efficiency, SD-v1.4training time (s): ~4500 -> ~440Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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