通过语义路由提升视觉概念删除的精准度与鲁棒性
MapRoute++: Surrogate-Guided Semantic Routing for Visual Concept Unlearning
- 引入任务特定目标与更丰富的概念表示，实现概念专属映射器选择
- 在五个概念类别上平均提升12.1%的消除-保留-鲁棒性指标
- 适合需要精准删除特定视觉概念且不破坏相邻内容的研究者
我们提交了参加Genμ 2.0挑战赛第3项任务的成果。基于MapRoute，提出任务特定训练目标、更丰富的概念表示以及针对概念的语义路由机制，用于选择特定映射器。该方法在保持无关及语义邻近概念完整性的同时，显著提升概念移除的鲁棒性。在官方基准测试中，使用Stable Diffusion v1.4评估的消融-保留-鲁棒性（ERR）指标下，我们的方法在五个概念类别上平均优于最先进基线12.1%，取得显著提升。
原文摘要 · Abstract (English)
We present our submission to Task 3 of the Gen$μ$ 2.0 Challenge on visual concept unlearning. Building on MapRoute, we introduce task-specific training objectives, richer concept representations, and semantic routing for concept-specific mapper selection. Our approach improves robust concept removal while preserving unrelated and semantically adjacent concepts. On the official benchmark, evaluated using the Erasing-Retention-Robustness (ERR) metric on Stable Diffusion v1.4, our method outperforms the state-of-the-art baseline by 12.1\% on average across the five concept categories, achieving substantial gains.
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。