用触发补丁评估样本可迁移性，实现更鲁棒的最近邻检索
Robust Nearest Neighbour Retrieval Using Targeted Manifold Manipulation
- 通过查询专属触发补丁，判断样本是否易被导向特定类别
- 在噪声下仍保持高检索准确率，优于传统距离度量方法
- 适合需要解释性与鲁棒性的分类与可解释AI场景
最近邻检索是分类和可解释AI流程的核心，但现有方法依赖人工调参特征层和距离度量。本文提出目标流形操控-最近邻（TMM-NN），重新定义检索机制：通过评估每个样本被定向扰动引导至特征流形特定区域的难易程度来定义邻域，而非依赖绝对几何距离。TMM-NN采用轻量级、查询相关的触发补丁，将其添加至查询图像，并弱化网络使含补丁输入被引导至假类别。与查询语义相似的样本仅需微小调整即可被高概率分类为假类别，而无关样本影响较小。基于该置信度排序候选样本，实现语义相关邻居的有效检索。鲁棒性分析与基准实验表明，该触发式排名在噪声干扰下及多种任务中均优于传统度量。
原文摘要 · Abstract (English)
Nearest-neighbour retrieval is central to classification and explainable-AI pipelines, but current practice relies on hand-tuning feature layers and distance metrics. We propose Targeted Manifold Manipulation-Nearest Neighbour (TMM-NN), which reconceptualises retrieval by assessing how readily each sample can be nudged into a designated region of the feature manifold; neighbourhoods are defined by a sample's responsiveness to a targeted perturbation rather than absolute geometric distance. TMM-NN implements this through a lightweight, query-specific trigger patch. The patch is added to the query image, and the network is weakly ``backdoored'' so that any input with the patch is steered toward a dummy class. Images similar to the query need only a slight shift and are classified as the dummy class with high probability, while dissimilar ones are less affected. By ranking candidates by this confidence, TMM-NN retrieves the most semantically related neighbours. Robustness analysis and benchmark experiments confirm this trigger-based ranking outperforms traditional metrics under noise and across diverse tasks.
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。