提出双层次去偏框架，解决可见光与红外行人重识别中的模态偏差问题。
Dual-level Modality Debiasing Learning for Unsupervised Visible-Infrared Person Re-Identification
- 用因果建模替代概率建模，从模型层面抑制模态偏差
- 通过数据、标签、特征三重去偏策略，阻断偏差传播路径
- 在多个基准数据集上实现更鲁棒的跨模态特征学习，适合多模态识别研究者
无监督可见光-红外行人重识别（USL-VI-ReID）通常采用两阶段学习：先单模态学习，再跨模态学习以缓解模态差异。然而该流程会引入模态偏差——单模态训练中学习到的模态特异性线索会传递至后续跨模态学习，损害身份判别与泛化能力。为此，本文提出双层次去偏学习（DMDL）框架，在模型与优化两个层面实现去偏。模型层面设计因果启发的调整干预（CAI）模块，以因果建模替代基于似然的建模，防止模态诱发的虚假关联；优化层面提出协同无偏训练（CBT）策略，通过模态特异性增强、标签精炼和特征对齐，阻断偏差在数据、标签与特征间的传播。大量实验表明，DMDL能实现模态不变特征学习，提升模型泛化性。代码已开源。
原文摘要 · Abstract (English)
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. The code is available at https://github.com/priester3/DMDL.
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。