Abstract
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.
Abstract (translated)
在无监督的可见光-红外行人重识别（USL-VI-ReID）中，两阶段学习管道已经取得了显著成果。它首先进行单模态学习，然后执行跨模态学习以解决模态差异问题。尽管这一流程显示出前景，但不可避免地引入了模态偏见：在单一模态训练中学到的特定于某一模态的线索自然会传递到随后的跨模态学习中，从而损害身份鉴别能力和泛化能力。 为了解决这个问题，我们提出了一种双层级消偏学习（DMDL）框架，在模型和优化两个层面实施了消偏策略。在模型层面上，我们提出了一个因果启发调整干预（CAI）模块，该模块用因果建模替代基于似然性的建模方法，防止由特定模态导致的虚假模式被引入系统中，从而生成低偏见的模型。在优化层面上，则引入了一种协作无偏训练（CBT）策略，通过整合特定于某一模态的数据增强、标签精炼和特征对齐来中断数据、标签及特征之间的模态偏见传播。 广泛的基准数据集实验表明，DMDL框架能够实现模态不变的特征学习，并提高模型的泛化能力。
URL
https://arxiv.org/abs/2512.03745
