Despite recent remarkable progress, person re-identification (ReID) still suffers from a shortage of annotated training data. To deal with this problem, there has been a boost of interest in developing various data augmentation methods. In this paper, we are devoted to developing an end-to-end joint representation learning framework for the ReID task on the basis of a novel data augmentation strategy. Specifically, we regard the original training dataset as a source domain and generate the counterpart augmented domains through image channel shuffling. Accordingly, we design a symmetric classification network for ReID learning. By investigating the domain-level and identity-level relationship between domains, we use the idea of negative transfer and structural consistency to optimize the network for learning discriminative feature embeddings. Comprehensive experiments on some benchmark datasets demonstrate the effectiveness and robustness of our proposed approach. Source code is released at: https://github.com/flychen321/negative_transfer_reid.

尽管最近取得了显着进步，但人员重新识别（ReID）仍然受到缺少带注释的训练数据的困扰。为了解决这个问题，开发各种数据增强方法的兴趣得到了提高。在本文中，我们致力于在一种新颖的数据扩充策略的基础上为ReID任务开发端到端联合表示学习框架。具体来说，我们将原始训练数据集视为源域，并通过图像通道改组生成对应的增强域。因此，我们设计了用于ReID学习的对称分类网络。通过研究域之间的域级别和身份级别关系，我们使用负迁移和结构一致性的思想来优化用于学习判别性特征嵌入的网络。在一些基准数据集上的综合实验证明了我们提出的方法的有效性和鲁棒性。提供了可重复性的源代码，并将在以下网址发布：https://github.com/flychen321/negative_transfer_reid。