Unsupervised person re-identification (Re-ID) aims to retrieve person images across cameras without any identity labels. Most clustering-based methods roughly divide image features into clusters and neglect the feature distribution noise caused by domain shifts among different cameras, leading to inevitable performance degradation. To address this challenge, we propose a novel label refinement framework with clustering intra-camera similarity. Intra-camera feature distribution pays more attention to the appearance of pedestrians and labels are more reliable. We conduct intra-camera training to get local clusters in each camera, respectively, and refine inter-camera clusters with local results. We hence train the Re-ID model with refined reliable pseudo labels in a self-paced way. Extensive experiments demonstrate that the proposed method surpasses state-of-the-art performance.

翻译：无监督行人重识别旨在无身份标签的情况下跨摄像头检索行人图像。多数基于聚类的方法粗略地将图像特征划分为簇，而忽视了不同摄像头间域偏移引起的特征分布噪声，导致性能不可避免的下降。为解决这一挑战，我们提出了一种新颖的基于帧内相似度聚类的标签细化框架。帧内特征分布更关注行人的外观特征，且标签更为可靠。我们通过帧内训练分别获取每个摄像头的局部簇，并利用局部结果优化跨摄像头聚类。进而以自步方式利用细化的可靠伪标签训练重识别模型。大量实验表明，所提方法超越了当前最先进性能。