Unsupervised domain adaptation (UDA) for person re-identification (re-ID) is a challenging task due to large variations in human classes, illuminations, camera views, and so on. Currently, existing UDA methods focus on two-domain adaptation and are generally trained on one labeled source set and adapted on the other unlabeled target set. In this article, we put forward a new issue on person re-ID, namely, unsupervised multi-target domain adaptation (UMDA). It involves one labeled source set and multiple unlabeled target sets, which is more reasonable for practical real-world applications. Enabling UMDA has to learn the consistency for multiple domains, which is significantly different from the UDA problem. To ensure distribution consistency and learn the discriminative embedding, we further propose the Camera Identity-guided Distribution Consistency method that performs an alignment operation for multiple domains. The camera identities are encoded into the image semantic information to facilitate the adaptation of features. According to our knowledge, this is the first attempt on the unsupervised multi-target domain adaptation learning. Extensive experiments are executed on Market-1501, DukeMTMC-reID, MSMT17, PersonX, and CUHK03, and our method has achieved very competitive re-ID accuracy in multi-target domains against numerous state-of-the-art methods.

中文翻译：

---

一种摄像机身份引导的无监督多目标域人员重新识别分布一致性方法

由于人类类别、照明、相机视图等的巨大变化，用于人员重新识别 (re-ID) 的无监督域适应 (UDA) 是一项具有挑战性的任务。目前，现有的 UDA 方法专注于两域自适应，通常在一个标记的源集上进行训练，并在另一个未标记的目标集上进行自适应。在本文中，我们提出了关于person re-ID的一个新问题，即无监督多目标域自适应（UMDA）。它涉及一个标记的源集和多个未标记的目标集，这对于实际的实际应用更为合理。启用 UMDA 必须学习多个域的一致性，这与 UDA 问题有很大不同。为了确保分布的一致性并学习判别嵌入，我们进一步提出了Camera Identity-guided Distribution Consistency方法，该方法对多个域执行对齐操作。相机身份被编码到图像语义信息中，以促进特征的适应。据我们所知，这是无监督多目标域自适应学习的首次尝试。在 Market-1501、DukeMTMC-reID、MSMT17、PersonX 和 CUHK03 上进行了广泛的实验，我们的方法在多目标域中实现了与众多最先进的方法相比极具竞争力的 re-ID 准确性。这是无监督多目标域自适应学习的第一次尝试。在 Market-1501、DukeMTMC-reID、MSMT17、PersonX 和 CUHK03 上进行了广泛的实验，我们的方法在多目标域中实现了与众多最先进的方法相比极具竞争力的 re-ID 准确性。这是无监督多目标域自适应学习的第一次尝试。在 Market-1501、DukeMTMC-reID、MSMT17、PersonX 和 CUHK03 上进行了广泛的实验，我们的方法在多目标域中实现了与众多最先进的方法相比极具竞争力的 re-ID 准确性。