Adaptive Metric Learning for People Re-Identification
Adaptive Metric Learning for People Re-Identification
复制标题
DOI：
10.1587/transinf.2013edp7451
复制
发表时间：
2014-11
期刊：
影响因子：
--
通讯作者：
Guanwen Zhang;Jien Kato;Yu Wang;K. Mase
中科院分区：
文献类型：
--
作者：
Guanwen Zhang;Jien Kato;Yu Wang;K. Mase
多镜头人物再识别中存在两个内在问题：（1）摄像机视角、光照和姿势的非刚性变形的巨大差异使得类内方差甚至大于类间方差;（2）在现实的再识别场景中，只有少数训练数据可用于学习任务。在我们之前的工作中，我们提出了一个局部距离比较框架来处理第一个问题。在本文中，为了处理第二个问题（即，为了从有限的训练数据中获得可靠的距离度量），我们提出了一种自适应学习方法来学习自适应距离度量，该方法集成了从大的现有辅助数据集学习的先验知识和从小得多的训练数据集提取的任务特定信息。在多个公共基准数据集上的实验结果表明，结合局部距离比较框架，我们的自适应学习方法优于传统方法的上级。关键词：多镜头人物再识别，自适应度量学习，局部距离比较
There exist two intrinsic issues in multiple-shot person reidentification: (1) large differences in camera view, illumination, and nonrigid deformation of posture that make the intra-class variance even larger than the inter-class variance; (2) only a few training data that are available for learning tasks in a realistic re-identification scenario. In our previous work, we proposed a local distance comparison framework to deal with the first issue. In this paper, to deal with the second issue (i.e., to derive a reliable distance metric from limited training data), we propose an adaptive learning method to learn an adaptive distance metric, which integrates prior knowledge learned from a large existing auxiliary dataset and task-specific information extracted from a much smaller training dataset. Experimental results on several public benchmark datasets show that combined with the local distance comparison framework, our adaptive learning method is superior to conventional approaches. key words: multiple-shot people re-identification, adaptive metric learning, local distance comparison