In cloth-changing person re-identification (CCReID), it is critical to learn clothes-invariant feature, which can provide discriminative ID features that remain robust against clothing changes. However, a spurious correlation currently limits existing ReID methods from effectively extracting these clothing-invariant features. This spurious correlation arises from clothing ownership: clothing is rarely shared across different identities, so models tend to memorize clothing cues for identity recognition, and this strategy generalizes poorly to unseen clothing. In this paper, we propose Causal Clothes-Invariant Learning (CCIL), which explicitly shifts CC-ReID from likelihood learning P (Y|X) to causal intervention learning P (Y|do(X)) to block the clothing shortcut. CCIL realizes this intervention through three modules: a Confounder Dictionary, an Intervention Module, and Disentangle Regularization. The causality-based modeling makes the entire model naturally clothes-invariant, effectively preventing the capture of spurious correlations in feature learning. Extensive experiments validate the effectiveness of CCIL. On PRCC and DeepChange datasets, CCIL achieves Rank-1 accuracies of 66.4% and 59.2%, outperforming state-of-the-art methods by 1.4 and 4.1 percentage points, respectively.

翻译：在换衣行人重识别（CC-ReID）任务中，学习与衣着无关的特征至关重要——这类特征能提供对衣物变化保持鲁棒的判别性身份特征。然而，现有重识别方法在有效提取这些衣物不变特征时受到虚假相关性的限制。这种虚假相关性源于衣物归属关系：不同身份的个体极少共享衣物，因此模型倾向于记忆衣着线索进行身份识别，这种策略在面对未见过的服装时泛化能力极差。本文提出因果式衣着不变学习（CCIL），明确将CC-ReID从似然学习P(Y|X)转变为因果干预学习P(Y|do(X))，以阻断衣物捷径。CCIL通过三个模块实现这种干预：混杂字典、干预模块和解耦正则化。基于因果关系的建模使整个模型天然具有衣物不变性，有效防止特征学习中捕获虚假相关性。大量实验验证了CCIL的有效性。在PRCC和DeepChange数据集上，CCIL分别达到66.4%和59.2%的Rank-1准确率，比当前最先进方法分别高出1.4和4.1个百分点。