Distance learning by treating negative samples differently and exploiting impostors with symmetric triplet constraint for person re-identification
Distance learning by treating negative samples differently and exploiting impostors with symmetric triplet constraint for person re-identification
复制标题
DOI：
10.1109/icme.2016.7552885
复制
发表时间：
2016-07
期刊：
影响因子：
--
通讯作者：
Xiaoke Zhu;Xiaoyuan Jing;Fei Wu;Weishi Zheng;R. Hu;Chunxia Xiao;Chao Liang
中科院分区：
文献类型：
--
作者：
Xiaoke Zhu;Xiaoyuan Jing;Fei Wu;Weishi Zheng;R. Hu;Chunxia Xiao;Chao Liang
远程学习(DL)是一种有效的身份识别(PR-ID)技术。基于DL的方法通过利用样本中包含的区别性信息来学习距离度量。在PR-ID中，不同类型的负值样本具有不同的区分性信息量，冒名顶替者样本通常比其他可分离的负值样本(WSN样本)拥有更多的区分信息量。因此，如何充分利用DL过程中所有阴性样本所传递的不同判别信息是一个亟待研究的问题。在这篇文章中，我们提出了一种新的用于PR-ID的DL方法。具体地说，对于每个目标样本，我们将其负样本分为冒名顶替者样本和无线传感器网络样本。然后分别利用冒名顶替者和无线传感器网络样本来学习距离度量。对于冒名顶替者，我们设计了一个对称的三元组约束，要求冒名顶替者同时远离其对应的正样本对的两个样本；对于WSN样本，我们要求它们保持良好的可分性。在三个基准数据集上的实验结果证明了该方法的有效性和高效性。
Distance learning (DL) is an effective technique for person reidentification (PR-ID). DL based methods learn the distance metric by exploiting the discriminative information contained in samples. In PR-ID, different types of negative samples own different amounts of discriminative information, and impostor samples usually own more than other well separable negative samples (WSN-samples). Therefore, how to make full use of the different discriminative information conveyed by all negative samples in the DL process is a critical issue to be investigated. In this paper, we propose a novel DL approach for PR-ID. Specifically, for each target sample, we divide its negative samples into impostors and WSN-samples. Then we learn the distance metric by utilizing impostors and WSN-samples differently. For impostors, we design a symmetric triplet constraint, which requires the impostor to be far away from both samples of its corresponding positive sample pair simultaneously; for WSN-samples, we require them to keep their favorable separability. Experimental results on three benchmark datasets demonstrate the effectiveness and efficiency of our approach.