通过图文协作实现精准概念擦除，提升生成安全性和可控性。
Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration
- 构建连续凸概念流形与分层视觉表征，实现图文协同擦除。
- 在多基准测试中显著优于现有方法，擦除精度与内容保真度双高。
- 适合需要高安全性与可控性的图像生成场景，如内容审核与隐私保护。
文本到图像生成模型虽已达到高度保真与多样性，但因大规模训练数据中的隐含偏见，可能生成不安全或不期望的内容。现有概念擦除方法（纯文本或图像引导）存在权衡：文本方法常无法完全抑制概念，而直接图像引导方法易过度擦除无关内容。本文提出TICoE——一种基于连续凸概念流形与分层视觉表示学习的图文协同擦除框架，可精确移除目标概念并保留无关语义与视觉内容。为客观评估擦除质量，我们进一步引入以保真度为导向的评价策略，衡量擦除后内容的可用性。在多个基准测试上的实验表明，TICoE在概念擦除精度与内容保真度方面均超越现有方法，使文本到图像生成更安全、更可控。代码已开源：https://github.com/OpenAscent-L/TICoE.git。
原文摘要 · Abstract (English)
Text-to-image generative models have achieved impressive fidelity and diversity, but can inadvertently produce unsafe or undesirable content due to implicit biases embedded in large-scale training datasets. Existing concept erasure methods, whether text-only or image-assisted, face trade-offs: textual approaches often fail to fully suppress concepts, while naive image-guided methods risk over-erasing unrelated content. We propose TICoE, a text-image Collaborative Erasing framework that achieves precise and faithful concept removal through a continuous convex concept manifold and hierarchical visual representation learning. TICoE precisely removes target concepts while preserving unrelated semantic and visual content. To objectively assess the quality of erasure, we further introduce a fidelity-oriented evaluation strategy that measures post-erasure usability. Experiments on multiple benchmarks show that TICoE surpasses prior methods in concept removal precision and content fidelity, enabling safer, more controllable text-to-image generation. Our code is available at https://github.com/OpenAscent-L/TICoE.git
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。