发表机构
University of Science and Technology of China; Anhui Province Key Laboratory of Digital Security; The Chinese University of Hong Kong（中国科学技术大学; 安徽省数字安全重点实验室; 香港中文大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对行人重识别中基于邻居方法仅依赖亲和关系、受噪声邻居影响的问题，提出ANFI方法，不仅建模亲和关系与差异关系，还用自适应加权，通过新邻域相似度导出差异关系，经噪声关系监督训练，实验证明其在多种设置下的优越性。
AI 中文摘要
在行人重识别中，基于邻居的方法通过与邻居样本交互获得更鲁棒的表示并取得了显著成功。然而，现有方法仅依赖亲和关系，其成功严重依赖所选邻居的可靠性。我们发现仅基于亲和性的交互在具有挑战性的场景中常因噪声邻居的不可避免存在而失败。为在噪声邻域中实现有效交互，我们在不同可靠性条件下重新审视基于邻居的方法并提出一种新颖的自适应邻居特征交互（ANFI）方法。ANFI的核心思想是考虑噪声邻居的负面影响，使样本与误报邻居保持可区分。与现有方法不同，ANFI不仅对亲和关系建模，还对差异关系建模，并对这两种关系采用逐样本自适应加权。鉴于从噪声邻居捕捉负面影响与传统关系学习有显著差异，我们从一种新的邻域相似度导出差异关系，其提供比成对相似度更多的信息。此外，我们提出噪声关系监督（NRS）来训练ANFI，逐步将对噪声关系的鲁棒性注入模型。在标准、跨模态和跨域设置下进行的广泛实验，包括与基于邻居的方法和重排序方法的比较，证明了我们的方法在各种邻居分布上的优越性。
英文摘要
In person re-identification, neighbor-based methods have achieved significant success by interacting with neighbor samples to obtain more robust representations. However, existing methods rely only on affinity relations, causing their success to depend heavily on the reliability of selected neighbors. We find that affinity-only interaction often fails in challenging scenarios due to the inevitable presence of noisy neighbors. To enable effective interactions under noisy neighborhoods, we revisit neighbor-based methods under distinct reliability conditions and propose a novel Adaptive Neighbor Feature Interaction (ANFI) method. The core idea of ANFI is to account for negative effects from noisy neighbors, allowing samples to remain distinguishable from false positive neighbors. Unlike existing methods, ANFI models not only affinity relations but also discrepancy relations, and employs sample-wise adaptive weighting for these two types of relations. Given that capturing negative effects from noisy neighbors differs significantly from traditional relation learning, we derive discrepancy relations from a new neighborhood similarity, which provides more information than pairwise similarity. In addition, we propose Noisy Relation Supervision (NRS) to train ANFI, gradually injecting robustness to noisy relations into the model. Extensive experiments conducted under standard, cross-modal, and cross-domain settings, including comparisons with neighbor-based methods and re-ranking methods, demonstrate the superiority of our method across various neighbor distributions.
Commentsaccepted by ECCV2026
