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. 多模态人工智能系统全国重点实验室
  5. 人工智能与机器学习
Learning to Align via Wasserstein for Person Re-Identification

文献类型：期刊论文

作者Zhang, Zhizhong1,2; Xie, Yuan3; Li, Ding1,2; Zhang, Wensheng1,2; Tian, Qi4
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2020
卷号29页码:7104-7116
关键词Semantics Heating systems Measurement Learning systems Training Estimation Feature extraction Person re-identification deep metric learning convolutional neural network Wasserstein distance
ISSN号1057-7149
DOI10.1109/TIP.2020.2998931
通讯作者Zhang, Wensheng(zhangwenshengia@hotmail.com) ; Tian, Qi(tian.qi1@huawei.com)
英文摘要Existing successful person re-identification (Re-ID) models often employ the part-level representation to extract the fine-grained information, but commonly use the loss that is particularly designed for global features, ignoring the relationship between semantic parts. In this paper, we present a novel triplet loss that emphasizes the salient parts and also takes the consideration of alignment. This loss is based on the crossing-bing matching metric that also known as Wasserstein Distance. It measures how much effort it would take to move the embeddings of local features to align two distributions, such that it is able to find an optimal transport matrix to re-weight the distance of different local parts. The distributions in support of local parts is produced via a new attention mechanism, which is calculated by the inner product between high-level global feature and local features, representing the importance of different semantic parts w.r.t. identification. We show that the obtained optimal transport matrix can not only distinguish the relevant and misleading parts, and hence assign different weights to them, but also rectify the original distance according to the learned distributions, resulting in an elegant solution for the mis-alignment issue. Besides, the proposed method is easily implemented in most Re-ID learning system with end-to-end training style, and can obviously improve their performance. Extensive experiments and comparisons with recent Re-ID methods manifest the competitive performance of our method.
WOS关键词NETWORK
资助项目National Key Research and Development Program of China[2017YFC0803700] ; National Natural Science Foundation of China[U1636220] ; National Natural Science Foundation of China[61772524] ; National Natural Science Foundation of China[61961160707] ; National Natural Science Foundation of China[61976212] ; Beijing Municipal Natural Science Foundation[4182067] ; Fundamental Research Funds for the Central Universities ; Shanghai Key Laboratory of Trustworthy Computing
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000546910100015
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China ; Beijing Municipal Natural Science Foundation ; Fundamental Research Funds for the Central Universities ; Shanghai Key Laboratory of Trustworthy Computing
源URL[http://ir.ia.ac.cn/handle/173211/40047]  
专题精密感知与控制研究中心_人工智能与机器学习
通讯作者Zhang, Wensheng; Tian, Qi
作者单位1.Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China
3.East China Normal Univ, Sch Comp Sci & Software Engn, Shanghai 200241, Peoples R China
4.Huawei Technol, Cloud BU, Shenzhen 51800, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Zhizhong,Xie, Yuan,Li, Ding,et al. Learning to Align via Wasserstein for Person Re-Identification[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2020,29:7104-7116.
APA Zhang, Zhizhong,Xie, Yuan,Li, Ding,Zhang, Wensheng,&Tian, Qi.(2020).Learning to Align via Wasserstein for Person Re-Identification.IEEE TRANSACTIONS ON IMAGE PROCESSING,29,7104-7116.
MLA Zhang, Zhizhong,et al."Learning to Align via Wasserstein for Person Re-Identification".IEEE TRANSACTIONS ON IMAGE PROCESSING 29(2020):7104-7116.

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。