arXiv 1703.056932017-03cs.CV

基于SVDNet的行人检索

SVDNet for Pedestrian Retrieval

Tsinghua University（清华大学）；University of Technology Sydney（悉尼科技大学）；University of Chinese Academy of Sciences（中国科学院大学）

Yifan Sun, Liang Zheng, Weijian Deng, Shengjin Wang

备注：: accepted as spotlight to ICCV 2017

摘要：

本文提出了SVDNet的检索问题，重点是应用的人重新识别（重新ID）。我们将卷积神经元网络（CNN）中的全连接（FC）层内的每个权重向量视为投影基础。据观察，权重向量通常高度相关。这个问题导致FC描述符的条目之间的相关性，并损害基于欧几里德距离的检索性能。为了解决这个问题，本文提出了使用奇异向量分解（SVD）优化深度表示学习过程。具体来说，通过约束和松弛迭代（RRI）训练方案，我们能够在CNN训练中迭代地整合正交约束，从而产生所谓的SVDNet。我们在Market-1501、CUHK 03和Duke数据集上进行了实验，结果表明，RRI有效地降低了投影向量之间的相关性，产生了更具鉴别力的FC描述符，并显着提高了re-ID的准确性。例如，在Market-1501数据集上，CaffeNet的rank-1准确率从55.3%提高到80.5%，ResNet-50从73.8%提高到82.3%。

英文摘要：

This paper proposes the SVDNet for retrieval problems, with focus on the application of person re-identification (re-ID). We view each weight vector within a fully connected (FC) layer in a convolutional neuron network (CNN) as a projection basis. It is observed that the weight vectors are usually highly correlated. This problem leads to correlations among entries of the FC descriptor, and compromises the retrieval performance based on the Euclidean distance. To address the problem, this paper proposes to optimize the deep representation learning process with Singular Vector Decomposition (SVD). Specifically, with the restraint and relaxation iteration (RRI) training scheme, we are able to iteratively integrate the orthogonality constraint in CNN training, yielding the so-called SVDNet. We conduct experiments on the Market-1501, CUHK03, and Duke datasets, and show that RRI effectively reduces the correlation among the projection vectors, produces more discriminative FC descriptors, and significantly improves the re-ID accuracy. On the Market-1501 dataset, for instance, rank-1 accuracy is improved from 55.3% to 80.5% for CaffeNet, and from 73.8% to 82.3% for ResNet-50.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

摘要：

英文摘要：

相关论文