Person Re-Identification by Dual-Regularized KISS Metric Learning

Person Re-Identification by Dual-Regularized KISS Metric Learning
复制标题

通过双正则 KISS 度量学习进行人员重新识别

DOI:
10.1109/tip.2016.2553446
复制
发表时间:
2016-06
影响因子:
10.6
通讯作者:
Yuan Yan Tang
Yuan Yan Tang
中科院分区:
计算机科学1区
文献类型:
--
作者:
Dapeng Tao;Yanan Guo;Mingli Song;Yaotang Li;Zhengtao Yu;Yuan Yan Tang

文献摘要

参考文献

被引文献

相似文献

人员重新识别的目的是匹配来自不同位置的不同相机视图中的行人图像。这是一个具有挑战性的智能视频监控问题,仍然是一个活跃的研究领域,由于需要提高性能。人的重新识别包括两个主要步骤:特征表示和度量学习。虽然保持简单和直接(KISS)度量学习方法的区别性距离度量学习已被证明是有效的人重新识别,估计的逆协方差矩阵是不稳定的,甚至可能不存在时,训练集很小,导致性能不佳。在这里,我们提出了双正则化KISS(DR-KISS)度量学习。通过正则化两个协方差矩阵,DR-KISS通过减少对两个估计协方差矩阵的大特征值的高估来改进KISS,并且这样做可以保证协方差矩阵是不可逆的。此外,我们还提供了理论分析来支持这些动机。具体来说,我们首先证明为什么正则化是必要的。然后,我们证明了所提出的方法是强大的推广。我们在三个具有挑战性的人重新识别数据集VIPeR,GRID和CUHK 01上进行了广泛的实验,并表明DR-KISS实现了新的最先进的性能。
Person re-identification aims to match the images of pedestrians across different camera views from different locations. This is a challenging intelligent video surveillance problem that remains an active area of research due to the need for performance improvement. Person re-identification involves two main steps: feature representation and metric learning. Although the keep it simple and straightforward (KISS) metric learning method for discriminative distance metric learning has been shown to be effective for the person re-identification, the estimation of the inverse of a covariance matrix is unstable and indeed may not exist when the training set is small, resulting in poor performance. Here, we present dual-regularized KISS (DR-KISS) metric learning. By regularizing the two covariance matrices, DR-KISS improves on KISS by reducing overestimation of large eigenvalues of the two estimated covariance matrices and, in doing so, guarantees that the covariance matrix is irreversible. Furthermore, we provide theoretical analyses for supporting the motivations. Specifically, we first prove why the regularization is necessary. Then, we prove that the proposed method is robust for generalization. We conduct extensive experiments on three challenging person re-identification datasets, VIPeR, GRID, and CUHK 01, and show that DR-KISS achieves new state-of-the-art performance.
DOI: 10.1109/tnnls.2015.2458986
发表时间: 2016-09
影响因子: 10.4
作者:
Tongliang Liu;D. Tao
通讯作者: Tongliang Liu;D. Tao
DOI: 10.5244/c.24.21
发表时间: 2010
影响因子: 4.9
作者:
B. Prosser;Weishi Zheng;S. Gong;T. Xiang
通讯作者: B. Prosser;Weishi Zheng;S. Gong;T. Xiang
DOI: 10.1023/b:visi.0000029664.99615.94
发表时间: 2004-11-01
影响因子: 19.5
作者:
Lowe, DG
通讯作者: Lowe, DG
DOI: 10.1007/978-94-024-1188-1_300116
发表时间: 2022
期刊: Hinduism and Tribal Religions
影响因子: --
作者:
Curriculum Vitae;J. A. Ward;Joshua Sharfstein;D. Webster;Rebecca Williams
通讯作者: Curriculum Vitae;J. A. Ward;Joshua Sharfstein;D. Webster;Rebecca Williams
DOI: 10.1109/tip.2015.2493446
发表时间: 2015-12-01
影响因子: 10.6
作者:
Dubey, Shiv Ram;Singh, Satish Kumar;Singh, Rajat Kumar
通讯作者: Singh, Rajat Kumar