AI Paper Atlas

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

Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers

Chi-Pin Huang, Kai-Po Chang, Chung-Ting Tsai, Yung-Hsuan Lai, Fu-En Yang, Yu-Chiang Frank Wang

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Concept erasure in diffusion models · 70 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
replace full-model fine-tuning with a lightweight eraser (ablation)Receler · CIFAR-10 object erasureAcc_R / Acc_L: Acc_R 39.4 -> 34.9; Acc_L 75.2 -> 77.4Improved
add concept-localized regularization to the eraser (ablation)Receler · CIFAR-10 object erasureAcc_L: 77.4 -> 79.8Improved
add adversarial prompt learning to the eraser (ablation)Receler · CIFAR-10 object erasureAcc_R: 34.9 -> 20.9Improved
add adversarial prompt learning without regularization (ablation)Receler · CIFAR-10 object erasureAcc_L: 77.4 -> 76.2Hurt
combine regularization and adversarial prompt learning (ablation)Receler · CIFAR-10 object erasureAcc_R / Acc_L: Acc_R 17.6; Acc_L 82.1Improved
use Receler instead of ESDSD v1.4 concept erasing · CIFAR-10 paraphrased promptsAcc_R: 39.9 -> 17.6Improved
use Receler instead of ESD/UCE on I2PSD v1.4 safety erasing · I2P overallinappropriate proportion (%): 31.3 -> 27.0 (vs UCE)Improved
use Receler on COCO-30K versus FMNnudity-erased SD v1.4 · COCO-30KFID-30K: 14.10 vs 13.52 (FMN)No clear effect
use Receler instead of other erasers against Ring-A-Bell nudity promptsnudity-erased SD v1.4 · Ring-A-Bell nudityfailure rate: 49.5% -> 1.1%Improved

Later papers that compared with this method

4 later accepted papers report Receler as a baseline in their results tables; 3 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