Unsupervised person re-identification aims to retrieve images of a specified person without identity labels. Many recent unsupervised Re-ID approaches adopt clustering-based methods to measure cross-camera feature similarity to roughly divide images into clusters. They ignore the feature distribution discrepancy induced by camera domain gap, resulting in the unavoidable performance degradation. Camera information is usually available, and the feature distribution in the single camera usually focuses more on the appearance of the individual and has less intra-identity variance. Inspired by the observation, we introduce a \textbf{C}amera-\textbf{A}ware \textbf{L}abel \textbf{R}efinement~(CALR) framework that reduces camera discrepancy by clustering intra-camera similarity. Specifically, we employ intra-camera training to obtain reliable local pseudo labels within each camera, and then refine global labels generated by inter-camera clustering and train the discriminative model using more reliable global pseudo labels in a self-paced manner. Meanwhile, we develop a camera-alignment module to align feature distributions under different cameras, which could help deal with the camera variance further. Extensive experiments validate the superiority of our proposed method over state-of-the-art approaches. The code is accessible at https://github.com/leeBooMla/CALR.

翻译：无监督行人重识别旨在无身份标签的情况下检索指定行人的图像。近年来许多无监督行人重识别方法采用基于聚类的技术度量跨相机特征相似性，以粗略地将图像划分为聚类簇。然而这些方法忽略了相机域差异导致的特征分布不一致，不可避免地造成性能退化。相机信息通常是可获取的，且单相机内的特征分布往往更关注个体外观，类内方差较小。受此观察启发，我们提出相机感知标签精炼（CALR）框架，通过聚类单相机内相似性来减少相机差异。具体而言，我们采用单相机内训练获取每个相机内可靠的局部伪标签，随后精炼跨相机聚类生成的全局标签，并以自步学习方式使用更可靠的全局伪标签训练判别模型。同时，我们开发相机对齐模块以对齐不同相机下的特征分布，进一步应对相机差异。大量实验验证了我们方法相较于现有最先进技术的优越性。代码可访问https://github.com/leeBooMla/CALR。