A novel deep model with multi-loss and efficient training for person re-identification
A novel deep model with multi-loss and efficient training for person re-identification
复制标题
一种新颖的多重损失深度模型，用于人员重新识别的高效训练
DOI：
10.1016/j.neucom.2018.03.073
复制
发表时间：
2019
期刊：
影响因子：
6
通讯作者：
Huang De Shuang
中科院分区：
文献类型：
--
作者：
Wu Di;Zheng Si Jia;Bao Wen Zheng;Zhang Xiao Ping;Yuan Chang An;Huang De Shuang
人物再识别（Person re-identification，PReID）的目的是从不重叠的摄像头中识别出同一个人，深度学习系统极大地促进了这一任务的实现。在这项研究中，我们回顾了PReID社区中两个广泛使用的CNN框架：识别模型和三重模型。我们提供了一个全面的概述这两种模式的优点和局限性，并提出了一个混合模型，结合了识别和三重模型的优点。具体而言，该模型采用三重损失，识别损失和中心损失，同时训练精心设计的网络。此外，其辨识子网络采用了丢弃策略。该模型在给定三个单元图像的情况下，输出三幅输入图像的同一性，并使不匹配图像对之间的欧氏距离大于匹配图像对之间的欧氏距离，同时减小同类图像的方差。在三个PReID基准数据集（CUHK 01，CUHK 03，Market-1501）上进行的大量比较实验表明，我们提出的架构在大多数情况下优于许多最先进的方法。
The purpose of Person re-identification (PReID) is to identify the same individual from the non-overlapping cameras, the task has been greatly promoted by the deep learning system. In this study, we review two widely-used CNN frameworks in the PReID community: identification model and triplet model. We provide a comprehensive overview of the advantages and limitations of the two models and present a hybrid model that combines the advantages of both identification and triplet models. Specifically, the proposed model employs triplet loss, identification loss and center loss to simultaneously train the carefully designed network. Furthermore, the dropout scheme is adopted by its identification subnetwork. Given a triplet unit images, the model can output the identities of the three input images and force the Euclidean distance between the mismatched pairs to be larger than those between the matched pairs as well as reduce the variance of the same class at the same time. Extensive comparative experiments on three PReID benchmark datasets (CUHK01, CUHK03, Market-1501) show that our proposed architecture outperforms many state of the art methods in most cases.