CE-SDWV: Effective and Efficient Concept Erasure for Text-to-Image Diffusion Models via a Semantic-Driven Word Vocabulary
机构 * College of Computer Science and Technology, Zhejiang University, China(浙江大学计算机科学与技术学院) ; Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi(阿布扎赫德莫罕默德·本·扎耶德人工智能大学) ; Department of Information Engineering and Computer Science, University of Trento, Italy(意大利特伦托大学信息工程与计算机科学系)
专题命中 文生图 :text-to-image(title,abstract);diffusion(title,abstract);分类 cs.CV
Comments 25 pages, 14 figures