Visible Thermal Person Re-Identification (VTReID) is essentially a cross-modality problem and widely encountered in real night-time surveillance scenarios, which is still in need of vigorous performance improvement. In this work, we design a simple but effective Hard Modality Alignment Network (HMAN) framework to learn modality-robust features. Since current VTReID works do not consider the cross-modality discrepancy imbalance, their models are likely to suffer from the selective alignment behavior. To solve this problem, we propose a novel Hard Modality Alignment (HMA) loss to simultaneously balance and reduce the modality discrepancies. Specifically, we mine the hard feature subspace with large modality discrepancies and abandon the easy feature subspace with small modality discrepancies to make the modality distributions more distinguishable. For mitigating the discrepancy imbalance, we pay more attention on reducing the modality discrepancies of the hard feature subspace than that of the easy feature subspace. Furthermore, we propose to jointly relieve the modality heterogeneity of global and local visual semantics to further boost the cross-modality retrieval performance. This paper experimentally demonstrates the effectiveness of the proposed method, achieving superior performance over the state-of-the-art methods on RegDB and SYSU-MM01 datasets.

可见热力人员重新识别（VTReID）本质上是一种跨模式问题，在实时夜间监视场景中经常遇到，仍然需要大力改进性能。在这项工作中，我们设计了一个简单但有效的硬模态对齐网络（HMAN）框架，以学习模态鲁棒性功能。由于当前VTReID的工作并未考虑跨模态差异的不平衡，因此其模型可能会遭受选择性对齐行为的困扰。为了解决这个问题，我们提出了一种新颖的硬模态对准（HMA）损失以同时平衡并减少模态差异。具体来说，我们挖掘具有较大模态差异的硬特征子空间，并放弃具有较小模态差异的易特征子空间，以使模态分布更加可区分。为了减轻差异不平衡，我们比起简单特征子空间更注重减少硬特征子空间的模态差异。此外，我们建议共同缓解全局和局部视觉语义的模态异质性，以进一步提高跨模态检索性能。本文通过实验证明了该方法的有效性，在RegDB和SYSU-MM01数据集上的性能优于最新方法。