Person Reidentification via Unsupervised Cross-View Metric Learning

Person Reidentification via Unsupervised Cross-View Metric Learning
复制标题

通过无监督的跨视图度量学习进行人员重新识别

DOI:
10.1109/tcyb.2019.2909480
复制
发表时间:
2019-04
影响因子:
11.8
通讯作者:
Xiaoqiang Lu
Xiaoqiang Lu
中科院分区:
计算机科学1区
文献类型:
--
作者:
Yachuang Feng;Yuan Yuan;Xiaoqiang Lu

文献摘要

参考文献

被引文献

相似文献

人物重新识别(Re-ID)旨在匹配多个非重叠相机视图中的个体观察结果。最近,基于度量学习的方法在解决这一任务中发挥了重要作用。然而,度量大多是以监督的方式学习的,其性能在很大程度上依赖于人工注释的数量和质量。同时,基于度量学习的算法通常将人的特征投影到一个公共子空间中,在该子空间中提取的特征被所有视图共享。然而,它可能会导致信息丢失,因为这些算法忽略了视图特定的功能。此外,他们假设不同观点的人样本来自同一分布。相反,这些样本更有可能服从不同的分布,由于视图条件的变化。为此,本文提出了一种基于数据分布特性的无监督跨视图度量学习方法。具体而言,每个视图中的人样本取自两个分布的混合物:一个模型相机视图之间的共同特性,另一个专注于视图特定的属性。在此基础上,我们引入了一个共享映射来探索共享功能。同时,我们构造特定于视图的映射,以提取和投影视图相关的功能到一个共同的子空间。因此,变换后的子空间中的样本遵循相同的分布,并配备了全面的表示。在本文中,这些映射学习在一个无监督的方式,通过聚类样本的投影空间。在5个跨视图数据集上的实验结果验证了该方法的有效性。
Person reidentification (Re-ID) aims to match observations of individuals across multiple nonoverlapping camera views. Recently, metric learning-based methods have played important roles in addressing this task. However, metrics are mostly learned in supervised manners, of which the performance relies heavily on the quantity and quality of manual annotations. Meanwhile, metric learning-based algorithms generally project person features into a common subspace, in which the extracted features are shared by all views. However, it may result in information loss since these algorithms neglect the view-specific features. Besides, they assume person samples of different views are taken from the same distribution. Conversely, these samples are more likely to obey different distributions due to view condition changes. To this end, this paper proposes an unsupervised cross-view metric learning method based on the properties of data distributions. Specifically, person samples in each view are taken from a mixture of two distributions: one models common prosperities among camera views and the other focuses on view-specific properties. Based on this, we introduce a shared mapping to explore the shared features. Meanwhile, we construct view-specific mappings to extract and project view-related features into a common subspace. As a result, samples in the transformed subspace follow the same distribution and are equipped with comprehensive representations. In this paper, these mappings are learned in an unsupervised manner by clustering samples in the projected space. Experimental results on five cross-view datasets validate the effectiveness of the proposed method.
通过双正则 KISS 度量学习进行人员重新识别
DOI: 10.1109/tip.2016.2553446
发表时间: 2016-06
影响因子: 10.6
作者:
Dapeng Tao;Yanan Guo;Mingli Song;Yaotang Li;Zhengtao Yu;Yuan Yan Tang
通讯作者: Yuan Yan Tang
DOI: 10.1109/cvpr.2016.152
发表时间: 2016-06
期刊: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
影响因子: --
作者:
Tetsu Matsukawa;Takahiro Okabe;Einoshin Suzuki;Yoichi Sato
通讯作者: Tetsu Matsukawa;Takahiro Okabe;Einoshin Suzuki;Yoichi Sato
DOI: --
发表时间: 2015-07
期刊: --
影响因子: --
作者:
Sheng Li;Ming Shao;Y. Fu
通讯作者: Sheng Li;Ming Shao;Y. Fu
DOI: 10.1016/s0377-0427(91)90073-s
发表时间: 2001
期刊: --
影响因子: --
作者:
Ph.D Preteem Ghosh
通讯作者: Ph.D Preteem Ghosh
DOI: 10.1109/icpr.2016.7900161
发表时间: 2016-12
期刊: 2016 23rd International Conference on Pattern Recognition (ICPR)
影响因子: --
作者:
Wei-Xiong He;Ying-Cong Chen;J. Lai
通讯作者: Wei-Xiong He;Ying-Cong Chen;J. Lai