Visible Thermal Person Re-Identification (VTReID) is a cross-modality retrieval problem in computer vision. Accurate VTReID is very challenging due to large modality discrepancies. In this work, we design a novel Multi-Patch Matching Network (MPMN) framework to simultaneously mitigate the heterogeneity of coarse-grained and fine-grained visual semantics. In view of cross-modality matching, we verify that aligning modality distributions of the original features is likely to suffer from the selective alignment behavior, i.e., only focuses on easiest dimensions or subspaces. Inspired by adversarial learning, we propose a new Multi-Patch Modality Alignment (MPMA) loss to jointly balance and reduce the modality discrepancies of multi-patch features by mining hard subspaces and abandoning easy subspaces. Since multi-patch features are potentially complementary to each other, the semantic correlations between different patches should be exploited during training. Motivated by knowledge distillation, we put forward a new Cross-Patch Correlation Distillation (CPCD) loss to transfer the semantic knowledges across different patches. To balance multi-patch tasks, an effective Patch-Aware Priority Attention (PAPA) method is further introduced to dynamically prioritize hard patch tasks during training. This paper experimentally demonstrates the effectiveness of the proposed methods, achieving superior performance over the state-of-the-art methods on RegDB and SYSU-MM01 datasets.

中文翻译：

---

深度多补丁匹配网络，可对热力人员进行重新识别

可见热人重识别(VTReID) 是计算机视觉中的跨模态检索问题。由于模态差异很大，准确的 VTReID 非常具有挑战性。在这项工作中，我们设计了一部小说多补丁匹配网络(MPMN) 框架同时减轻粗粒度和细粒度视觉语义的异质性。鉴于跨模态匹配，我们验证了原始特征的对齐方式分布很可能会受到选择性对齐行为的影响，即仅关注最简单的尺寸或子空间。受对抗学习的启发，我们提出了一项新的建议多补丁模式对齐(MPMA) loss 通过挖掘硬子空间和放弃简单子空间来联合平衡和减少多面体特征的模态差异。由于多补丁特征可能相互补充，因此在训练期间应利用不同补丁之间的语义相关性。在知识蒸馏的推动下，我们提出了一个新的交叉贴片相关蒸馏(CPCD) 损失以在不同的补丁之间传输语义知识。为了平衡多补丁任务，一个有效的补丁感知优先注意(PAPA) 方法被进一步引入，以在训练期间动态优先处理硬补丁任务。本文通过实验证明了所提出方法的有效性，在 RegDB 和 SYSU-MM01 数据集上实现了优于最先进方法的性能。