CE-SDWV: Effective and Efficient Concept Erasure for Text-to-Image Diffusion Models via a Semantic-Driven Word Vocabulary
- 8 July 2026
- journal article
- research article
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (7) , 336
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62402430)
- Natural Science Foundation of Zhejiang Province (LQN25F020008)
This publication has 56 references indexed in Scilit:
- Concept Corrector: Erase Concepts on the Fly for Text-to-Image Diffusion Models2026
- LaVie: High-Quality Video Generation with Cascaded Latent Diffusion ModelsInternational Journal of Computer Vision, 2024
- MaskDiffusion: Boosting Text-to-Image Consistency with Conditional MaskInternational Journal of Computer Vision, 2024
- Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models2024
- Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks2024
- R.A.C.E. : Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model2024
- Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers2024
- To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy to Generate Unsafe Images ... For Now2024
- Text2LIVE: Text-Driven Layered Image and Video Editing2022
- Microsoft COCO: Common Objects in Context2014