超越文本提示：通过文本-图像协同实现精确概念擦除
Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration
TICoE 用连续凸概念流形加分层视觉表征来定位并擦除目标概念，对做可控生成、个性化定制与生成内容安全的人提供了一个可复用的『文本-图像协同』擦除范式，其面向保真度的擦除后可用性评测协议也可直接用于评估编辑类方法是否误伤无关内容。
原文依据 We propose TICoE, a Text-Image Collaborative Erasing framework that achieves precise and faithful concept removal through a continuous convex concept manifold
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论文本到图像生成模型已具备令人印象深刻的保真度与多样性，但由于大规模训练数据集中隐含的偏见，它们可能无意间生成不安全或不良内容。现有的概念擦除方法，无论是仅基于文本的还是借助图像的，都面临权衡：文本方法往往无法完全抑制概念，而朴素的图像引导方法则有过度擦除无关内容的风险。我们提出 TICoE，一个文本-图像协同擦除框架，通过连续凸概念流形与分层视觉表征学习实现精确且忠实的概念移除。TICoE 在精确移除目标概念的同时保留无关的语义与视觉内容。为客观评估擦除质量，我们进一步提出一种面向保真度的评测策略，用于衡量擦除后的可用性。在多个基准上的实验表明，TICoE 在概念移除精确度与内容保真度上均优于先前方法，从而支持更安全、更可控的文本到图像生成。
英文原文摘要 1056 字符
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.