中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 智能感知与计算研究中心
Multi-Pseudo Regularized Label for Generated Data in Person Re-Identification

文献类型：期刊论文

作者Huang, Yan1; Xu, Jingsong1; Wu, Qiang1; Zheng, Zhedong2; Zhang, Zhaoxiang3; Zhang, Jian1
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2019-03-01
卷号28期号:3页码:1391-1403
关键词Person re-identification generated data virtual label semi-supervised learning
ISSN号1057-7149
DOI10.1109/TIP.2018.2874715
通讯作者Xu, Jingsong(jingsong.xu@uts.edu.au)
英文摘要Sufficient training data normally is required to train deeply learned models. However, due to the expensive manual process for a labeling large number of images (i.e., annotation), the amount of available training data (i.e., real data) is always limited. To produce more data for training a deep network, generative adversarial network can be used to generate artificial sample data (i.e., generated data). However, the generated data usually does not have annotation labels. To solve this problem, in this paper, we propose a virtual label called Multi-pseudo Regularized Label (MpRL) and assign it to the generated data. With MpRL, the generated data will be used as the supplementary of real training data to train a deep neural network in a semi-supervised learning fashion. To build the corresponding relationship between the real data and generated data, MpRL assigns each generated data a proper virtual label which reflects the likelihood of the affiliation of the generated data to pre-defined training classes in the real data domain. Unlike the traditional label which usually is a single integral number, the virtual label proposed in this paper is a set of weight-based values each individual of which is a number in (0,1] called multi-pseudo label and reflects the degree of relation between each generated data to every pre-defined class of real data. A comprehensive evaluation is carried out by adopting two state-of-the-art convolutional neural networks (CNNs) in our experiments to verify the effectiveness of MpRL. Experiments demonstrate that by assigning MpRL to generated data, we can further improve the person re-ID performance on five re-ID datasets, i.e., Market-1501, DukeMTMC-reID, CUHK03, VIPeR, and CUHK01. The proposed method obtains +6.29%, +6.30%, +5.58%, +5.84%, and +3.48% improvements in rank-1 accuracy over a strong CNN baseline on the five datasets, respectively, and outperforms state-of-the-art methods.
资助项目Australian Government Research Training Program Scholarship
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000451258900007
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构Australian Government Research Training Program Scholarship
源URL[http://ir.ia.ac.cn/handle/173211/25689]  
专题自动化研究所_智能感知与计算研究中心
通讯作者Xu, Jingsong
作者单位1.Univ Technol Sydney, Sch Elect & Data Engn, Global Big Data Technol Ctr, Ultimo, NSW 2007, Australia
2.Univ Technol Sydney, Sch Software, Ctr Artificial Intelligence, Ultimo, NSW 2007, Australia
3.Chinese Acad Sci, Inst Automat, Res Ctr Brain Inspired Intelligence, CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Huang, Yan,Xu, Jingsong,Wu, Qiang,et al. Multi-Pseudo Regularized Label for Generated Data in Person Re-Identification[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2019,28(3):1391-1403.
APA Huang, Yan,Xu, Jingsong,Wu, Qiang,Zheng, Zhedong,Zhang, Zhaoxiang,&Zhang, Jian.(2019).Multi-Pseudo Regularized Label for Generated Data in Person Re-Identification.IEEE TRANSACTIONS ON IMAGE PROCESSING,28(3),1391-1403.
MLA Huang, Yan,et al."Multi-Pseudo Regularized Label for Generated Data in Person Re-Identification".IEEE TRANSACTIONS ON IMAGE PROCESSING 28.3(2019):1391-1403.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。