IEEE Trans Cybern. 2022 Oct;52(10):10988-10998. doi: 10.1109/TCYB.2022.3183395. Epub 2022 Sep 19.
Visible infrared person reidentification (VI-REID) plays a critical role in night-time surveillance applications. Most methods attempt to reduce the cross-modality gap by extracting the modality-shared features. However, they neglect the distinct image-level discrepancies among heterogeneous pedestrian images. In this article, we propose a reciprocal bidirectional framework (RBDF) to achieve modality unification before discriminative feature learning. The bidirectional image translation subnetworks can learn two opposite mappings between visible and infrared modality. Particularly, we investigate the characteristics of the latent space and design a novel associated loss to pull close the distribution between the intermediate representations of two mappings. Mutual interaction between two opposite mappings helps the network generate heterogeneous images that have high similarity with the real images. Hence, the concatenation of original and generated images can eliminate the modality gap. During the feature learning procedure, the attention mechanism-based feature embedding network can learn more discriminative representations with the identity classification and feature metric learning. Experimental results indicate that our method achieves state-of-the-art performance. For instance, we achieve 54.41% mAP and 57.66% rank-1 accuracy on SYSU-MM01 dataset, outperforming the existing works by a large margin.
可见-近红外行人重识别（VI-REID）在夜间监控应用中起着至关重要的作用。大多数方法试图通过提取模态共享特征来缩小跨模态差距。然而，它们忽略了异构行人图像之间明显的图像级差异。在本文中，我们提出了一种互惠双向框架（RBDF），在进行判别特征学习之前实现模态统一。双向图像翻译子网可以学习可见模态和近红外模态之间的两个相反映射。特别是，我们研究了潜在空间的特征，并设计了一种新的关联损失来拉近两个映射的中间表示之间的分布。两个相反映射之间的相互作用有助于网络生成与真实图像具有高度相似性的异构图像。因此，原始图像和生成图像的拼接可以消除模态差距。在特征学习过程中，基于注意力机制的特征嵌入网络可以通过身份分类和特征度量学习来学习更具判别力的表示。实验结果表明，我们的方法达到了最先进的性能。例如，我们在 SYSU-MM01 数据集上实现了 54.41%的 mAP 和 57.66%的 rank-1 准确率，明显优于现有方法。
