Unsupervised domain adaptation person re-identification (UDA Re-ID) aims to leverage the pedestrian knowledge learned from labeled source domain to assist in learning the pedestrian knowledge in the unlabeled target domain. Most of existing investigations typically utilize single-class center clustering algorithms to group unlabeled target domain instances. Unfortunately, single-class center clustering algorithms tend to cluster pedestrian pictures from different identities into the same cluster, leading to inaccurate labels. Training with these noisy labels can undesirably deteriorate the accuracy of UDA Re-ID. Responding to the problem, we propose a multi-class center dynamic contrastive learning (MCC-DCL) for UDA Re-ID, which includes three main parts: multi-center clustering (MCC), dynamic pseudo-labeling (DPL), and dynamic contrastive learning (DCL). In order to reduce noisy labels generated during clustering, we introduce MCC method to generates reliable pseudo-labels for instances. Furthermore, to fully utilize the knowledge learned by the network during each iteration, we propose DPL method to optimizes the pseudo-labels of instances. Finally, for improving the discriminative performance of model and its tolerance to noisy labels, we propose DCL method that utilizes dynamic pseudo-labels and dynamic contrastive loss for supervised training. Comprehensive experiments and analyses demonstrate that MCC-DCL significantly outperforms existing approaches in UDA Re-ID tasks.

中文翻译：

---

用于无监督域适应人员重新识别的多类中心动态对比学习

无监督域适应行人重识别（UDA Re-ID）旨在利用从标记源域学习的行人知识来辅助学习未标记目标域中的行人知识。大多数现有研究通常利用单类中心聚类算法对未标记的目标域实例进行分组。不幸的是，单类中心聚类算法倾向于将不同身份的行人图片聚类到同一簇中，导致标签不准确。使用这些噪声标签进行训练可能会降低 UDA Re-ID 的准确性。针对该问题，我们提出了一种用于UDA Re-ID的多类中心动态对比学习（MCC-DCL），其中包括三个主要部分：多中心聚类（MCC）、动态伪标签（DPL）和动态伪标签（DPL）。对比学习（DCL）。为了减少聚类过程中产生的噪声标签，我们引入MCC方法来为实例生成可靠的伪标签。此外，为了充分利用网络在每次迭代过程中学到的知识，我们提出了 DPL 方法来优化实例的伪标签。最后，为了提高模型的判别性能及其对噪声标签的容忍度，我们提出了利用动态伪标签和动态对比损失进行监督训练的DCL方法。综合实验和分析表明，MCC-DCL 在 UDA Re-ID 任务中显着优于现有方法。