IEEE Trans Pattern Anal Mach Intell. 2020 Feb;42(2):371-385. doi: 10.1109/TPAMI.2019.2928294. Epub 2019 Jul 15.
Person re-identification (re-id) aims to match people across non-overlapping camera views in a public space. This is a challenging problem because the people captured in surveillance videos often wear similar clothing. Consequently, the differences in their appearance are typically subtle and only detectable at particular locations and scales. In this paper, we propose a deep re-id network (MuDeep) that is composed of two novel types of layers - a multi-scale deep learning layer, and a leader-based attention learning layer. Specifically, the former learns deep discriminative feature representations at different scales, while the latter utilizes the information from multiple scales to lead and determine the optimal weightings for each scale. The importance of different spatial locations for extracting discriminative features is learned explicitly via our leader-based attention learning layer. Extensive experiments are carried out to demonstrate that the proposed MuDeep outperforms the state-of-the-art on a number of benchmarks and has a better generalization ability under a domain generalization setting.
人体重识别（re-id）旨在匹配公共空间中不同摄像机视角下的人员。这是一个具有挑战性的问题，因为监控视频中捕获的人员通常穿着相似的衣服。因此，他们的外貌差异通常很细微，只能在特定的位置和尺度上检测到。在本文中，我们提出了一种深度 re-id 网络（MuDeep），它由两种新型的层组成——多尺度深度学习层和基于领导者的注意力学习层。具体来说，前者在不同的尺度上学习深度鉴别特征表示，而后者利用来自多个尺度的信息来引导和确定每个尺度的最优权重。通过我们的基于领导者的注意力学习层，可以显式地学习从不同空间位置提取鉴别特征的重要性。通过大量实验，我们证明了所提出的 MuDeep 在多个基准上优于现有技术，并且在域泛化设置下具有更好的泛化能力。
