无需微调，精准删除扩散模型中的特定概念而不伤及其他相关概念。
Erasing Without Collateral Damage: Precise Concept Removal in Diffusion Models
- 用保留概念的锚点计算新方向，避免误删相似特征。
- 单个参数控制删除与保留的平衡，效果优于现有方法。
- 闭式解无需训练，计算开销极低，适合快速部署。
无需微调的概念删除是控制文本到图像扩散模型的一种吸引人的方式，但精确删除常导致语义相关的非目标概念受损。现有值空间方法沿目标概念方向移除交叉注意力值的分量，隐式将目标身份与共享视觉结构视为同一信号，这是造成大量附带损害的原因。我们提出CARE，一种闭式概念删除算子，通过一个小规模保留概念锚点集计算保持子空间感知的方向，替代原始目标方向。该编辑直接应用于交叉注意力值空间，无需模型微调，仅增加可忽略的离线计算。单个收缩参数控制删除与保留的权衡。我们进一步证明该算子具有最小扰动解释，其投影形式保持保留子空间不变。在标准概念删除协议下的实验表明，本方法在保持非目标概念方面更忠实，同时在实例、风格和名人概念删除上保持竞争力。
原文摘要 · Abstract (English)
Training-free concept erasure is an attractive mechanism for controlling text-to-image diffusion models, but precise erasure often comes at the cost of damaging semantically related non-target concepts. Existing value-space methods remove the component of each cross-attention value along the target concept direction, implicitly treating target identity and shared visual structure as the same signal. We argue that this is the source of much of the collateral damage in prior preservation. We introduce CARE, a closed-form concept erasure operator that replaces the raw target direction with a kept-subspace-aware direction computed from a small bank of retained concept anchors. The resulting edit is applied directly in cross-attention value space, requires no model fine-tuning, and adds only a negligible offline computation. A single shrinkage parameter controls the erase-preserve trade-off. We further show that the operator admits a minimum-disturbance interpretation and, in its projection form, leaves the kept subspace invariant. Experiments under the standard concept-erasure protocol show that our method preserves non-target concepts more faithfully while maintaining competitive erasure across instance, style, and celebrity concepts. Code: https://github.com/parthupman/care
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。