提出新方法同时擦除图像中多个目标概念，提升生成安全性和可控性。
Mosaic: Compositional Multi-Concept Erasure via Vector Field Blending
- 基于向量场局部性动态构建概念掩码，实现多概念并行擦除。
- 在复杂场景中有效移除多个目标概念，且不破坏非目标内容。
- 适用于需要精确控制生成内容的高阶应用，如安全图像合成。
概念擦除已成为保障文本到图像（T2I）模型安全与伦理的重要研究方向。现有工作虽探索了多概念擦除，但通常假设每张图仅含一个目标概念，这一限制在现代基于流的T2I模型中日益凸显——这些模型可生成包含多个概念的复杂场景。为此，我们提出组合式多概念擦除新任务，旨在单个场景中同时移除多个目标概念。我们构建了CoME-Bench基准，涵盖同类与跨类场景。进一步提出Mosaic框架，针对基于流的T2I模型，利用目标概念在向量场中的空间局部性，动态生成概念专属掩码并选择性融合，无需额外优化。大量实验表明，Mosaic在复杂组合场景中有效擦除多个目标概念，同时保留非目标上下文。
原文摘要 · Abstract (English)
Concept erasure has emerged as a key research direction for ensuring safe and ethical image synthesis in Text-to-Image (T2I) models. While existing studies have explored concept erasure across multiple concepts, they typically assume only a single target concept per image, a limitation increasingly exposed by modern flow-based T2I models, which can generate complex scenes with multiple concepts simultaneously. To address this gap, we introduce compositional multi-concept erasure, a new task that aims to simultaneously remove multiple target concepts within a single scene. We propose CoME-Bench, a benchmark for evaluating compositional multi-concept erasure, which covers both intra- and cross-category scenarios. We further propose Mosaic, a novel framework for multi-concept erasure in flow-based T2I models, which exploits the spatial locality of target concepts in the vector field by dynamically constructing concept-specific masks and selectively blending them without additional optimization. Extensive experiments demonstrate that Mosaic effectively removes multiple target concepts in complex compositional scenes while preserving non-target contexts.
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。