Recently, cluster contrastive learning has been proven effective for object ReID by computing the contrastive loss between the individual features and the cluster memory. However, existing methods that use the individual features to momentum update the cluster memory will fluctuate over the training examples, especially for the outlier samples. Unlike the individual-based updating mechanism, the centroid-based updating mechanism that applies the mean feature of each cluster to update the cluster memory can reduce the impact of individual samples. Therefore, we formulate the individual-based updating and centroid-based updating mechanisms in a unified cluster contrastive framework, named Dual Cluster Contrastive framework (DCC), which maintains two types of memory banks: individual and centroid cluster memory banks. Significantly, the individual cluster memory considers just one individual at a time to take a single step for updating. The centroid cluster memory applies the mean feature of each cluster to update the corresponding cluster memory. During optimization, besides the vallina contrastive loss of each memory, a cross-view consistency constraint is applied to exchange the benefits of two memories for generating a discriminative description for the object ReID. Note that DCC can be easily applied for unsupervised or supervised object ReID by using ground-truth labels or the generated pseudo-labels. Extensive experiments on three benchmarks, \emph{e.g.,} Market-1501, MSMT17, and VeRi-776, under \textbf{supervised Object ReID} and \textbf{unsupervised Object ReID} demonstrate the superiority of the proposed DCC.

翻译：近年来，聚类对比学习通过计算个体特征与聚类记忆之间的对比损失，已被证明对目标重识别（ReID）是有效的。然而，现有方法使用个体特征对聚类记忆进行动量更新时，会因训练样本（尤其是离群样本）而产生波动。与基于个体的更新机制不同，基于质心的更新机制应用每个聚类的平均特征来更新聚类记忆，能够减少个体样本的影响。因此，我们将基于个体的更新机制和基于质心的更新机制统一到一个聚类对比框架中，称为双重聚类对比框架（DCC），该框架维护两种类型的内存库：个体聚类记忆库和质心聚类记忆库。值得注意的是，个体聚类记忆每次仅考虑一个个体进行单步更新；质心聚类记忆则应用每个聚类的平均特征来更新相应的聚类记忆。在优化过程中，除了每个内存的常规对比损失外，还应用了跨视图一致性约束，以交换两种记忆的优势，为目标重识别生成具有判别性的描述。需要指出的是，通过使用真实标签或生成的伪标签，DCC可以轻松应用于无监督或有监督的目标重识别。在三个基准数据集（例如 Market-1501、MSMT17 和 VeRi-776）上，针对有监督目标重识别和无监督目标重识别的大量实验，证明了所提出的 DCC 方法的优越性。