Discriminative regularized metric learning for person re-identification
2015 International Conference on Biometrics (ICB)(2015)
摘要
Person re-identification aims to match people across non-overlapping cameras, and recent advances have shown that metric learning is an effective technique for person re-identification. However, most existing metric learning methods suffer from the small sample size (SSS) problem due to the limited amount of labeled training samples. In this paper, we propose a new discriminative regularized metric learning (DRML) method for person re-identification. Specifically, we exploit discriminative information of training samples to regulate the eigenvalues of the intra-class and inter-class covariance matrices so that the distance metric estimated is less biased. Experimental results on three widely used datasets validate the effectiveness of our proposed method for person re-identification.
更多查看译文
关键词
discriminative regularized metric learning,person re-identification,nonoverlapping camera,metric learning method,small sample size problem,SSS problem,labeled training sample,DRML method,discriminative information,eigenvalue,intra-class covariance matrix,inter-class covariance matrix,distance metric
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络