Tang Yingzhi, Yang Xi, Wang Nannan, Song Bin, Gao Xinbo
IEEE Trans Image Process. 2020 Apr 13. doi: 10.1109/TIP.2020.2985545.
Person re-identification (re-ID) is a technique aiming to recognize person cross different cameras. Although some supervised methods have achieved favorable performance, they are far from practical application owing to the lack of labeled data. Thus, unsupervised person re-ID methods are in urgent need. Generally, the commonly used approach in existing unsupervised methods is to first utilize the source image dataset for generating a model in supervised manner, and then transfer the source image domain to the target image domain. However, images may lose their identity information after translation, and the distributions between different domains are far away. To solve these problems, we propose an image domain-to-domain translation method by keeping pedestrian's identity information and pulling closer the domains' distributions for unsupervised person re-ID tasks. Our work exploits the CycleGAN to transfer the existing labeled image domain to the unlabeled image domain. Specially, a Self-labeled Triplet Net is proposed to maintain the pedestrian identity information, and maximum mean discrepancy is introduced to pull the domain distribution closer. Extensive experiments have been conducted and the results demonstrate that the proposed method performs superiorly than the state-ofthe- art unsupervised methods on DukeMTMC-reID and Market- 1501.
行人重识别（re-ID）是一种旨在跨不同摄像头识别行人的技术。尽管一些监督方法取得了不错的性能，但由于缺乏标注数据，它们离实际应用还很远。因此，无监督行人重识别方法亟待发展。一般来说，现有无监督方法中常用的方法是首先利用源图像数据集以监督方式生成一个模型，然后将源图像域转移到目标图像域。然而，图像在转移后可能会丢失其身份信息，并且不同域之间的分布差异很大。为了解决这些问题，我们提出了一种图像域到域的转换方法，用于无监督行人重识别任务，该方法能保留行人的身份信息并拉近域之间的分布。我们的工作利用循环生成对抗网络（CycleGAN）将现有的标注图像域转移到未标注图像域。具体来说，我们提出了一个自标注三元组网络来保留行人身份信息，并引入最大均值差异来拉近域分布。我们进行了大量实验，结果表明，在杜克多模态交通监控数据集（DukeMTMC-reID）和市场1501数据集（Market-1501）上，所提出的方法比现有最先进的无监督方法表现更优。
