面向无监督行人重识别的相机感知标签细化
Camera-aware Label Refinement for Unsupervised Person Re-identification
AI总结：
针对无监督行人重识别中相机域差距导致特征分布差异的问题，提出CALR框架，通过相机内训练获取局部伪标签、细化全局标签并结合相机对齐模块，提升了识别性能。
摘要：
无监督行人重识别旨在无需身份标签的情况下检索指定行人的图像。近期许多无监督重识别方法采用基于聚类的方法来衡量跨相机特征相似度，将图像大致划分为簇，但忽略了相机域差距导致的特征分布差异，从而不可避免地造成性能下降。相机信息通常是可获取的，且单相机内的特征分布通常更关注个体外观，身份内方差更小。受此观察启发，我们提出相机感知标签细化（CALR）框架，通过聚类相机内相似度来减少相机差异。具体而言，我们采用相机内训练以在每个相机内获得可靠的局部伪标签，然后细化由相机间聚类生成的全局标签，并以自定进度的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，进一步帮助处理相机方差。大量实验验证了我们提出的方法优于现有技术。代码可在https://github.com/leeBooMla/CALR获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
