Two-stage learning pipeline has achieved promising results in unsupervised visible-infrared person re-identification (USL-VI-ReID). It first performs single-modality learning and then operates cross-modality learning to tackle the modality discrepancy. Although promising, this pipeline inevitably introduces modality bias: modality-specific cues learned in the single-modality training naturally propagate into the following cross-modality learning, impairing identity discrimination and generalization. To address this issue, we propose a Dual-level Modality Debiasing Learning (DMDL) framework that implements debiasing at both the model and optimization levels. At the model level, we propose a Causality-inspired Adjustment Intervention (CAI) module that replaces likelihood-based modeling with causal modeling, preventing modality-induced spurious patterns from being introduced, leading to a low-biased model. At the optimization level, a Collaborative Bias-free Training (CBT) strategy is introduced to interrupt the propagation of modality bias across data, labels, and features by integrating modality-specific augmentation, label refinement, and feature alignment. Extensive experiments on benchmark datasets demonstrate that DMDL could enable modality-invariant feature learning and a more generalized model.

翻译：两阶段学习流程在无监督可见光-红外行人重识别（USL-VI-ReID）中取得了显著成果。该流程首先进行单模态学习，随后执行跨模态学习以处理模态差异。尽管效果显著，此流程不可避免地引入了模态偏差：在单模态训练中习得的模态特定线索会自然传递至后续跨模态学习阶段，从而损害身份判别能力与泛化性能。为解决此问题，我们提出了一种双层级模态去偏学习框架，该框架在模型层面与优化层面同时实施去偏操作。在模型层面，我们设计了因果启发的调整干预模块，该模块以因果建模替代基于似然的建模，防止引入由模态引发的虚假模式，从而构建低偏差模型。在优化层面，我们引入了协同无偏训练策略，通过整合模态特定数据增强、标签精细化处理与特征对齐，阻断模态偏差在数据、标签及特征间的传递。在多个基准数据集上的大量实验表明，DMDL能够实现模态不变的特征学习并得到更具泛化能力的模型。