Regularized local metric learning for person re-identification
Regularized local metric learning for person re-identification
复制标题
DOI：
10.1016/j.patrec.2015.05.001
复制
发表时间：
2015-12
期刊：
影响因子：
--
通讯作者：
Venice Erin Liong;Jiwen Lu;Yongxin Ge
中科院分区：
文献类型：
--
作者：
Venice Erin Liong;Jiwen Lu;Yongxin Ge
本文提出了一种正则化局部度量学习（RLML）的人再识别方法。现有的基于度量学习的人体再识别方法只学习一个距离度量来度量每对人体图像的相似性，而我们的方法结合全局和局部度量来表示类内和类间方差。通过这样做，我们利用训练数据的局部分布来避免过拟合问题。此外，为了解决大多数人再识别系统缺乏训练样本的问题，我们的方法还以参数方式调节协方差矩阵，以便更好地利用判别信息。在四个广泛使用的数据集上的实验结果表明，我们提出的RLML优于现有的度量学习和最先进的人物再识别方法。
In this paper, we propose a regularized local metric learning (RLML) method for person re-identification. Unlike existing metric learning based person re-identification methods which learn a single distance metric to measure the similarity of each pair of human body images, our method combines global and local metrics to represent the within-class and between-class variances. By doing so, we utilize the local distribution of the training data to avoid the overfitting problem. In addition, to address the lacking of training samples in most person re-identification systems, our method also regulates the covariance matrices in a parametric manner, so that discriminative information can be better exploited. Experimental results on four widely used datasets demonstrate the advantage of our proposed RLML over both existing metric learning and state-of-the-art person re-identification methods.