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. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Cross-domain activity recognition via substructural optimal transport

文献类型：期刊论文

作者Lu, Wang2,3; Chen, Yiqiang2,3; Wang, Jindong1; Qin, Xin2,3
刊名NEUROCOMPUTING
出版日期2021-09-24
卷号454页码:65-75
ISSN号0925-2312
关键词Ubiquitous computing Transfer learning Domain adaptation Optimal transport Clustering
DOI10.1016/j.neucom.2021.04.124
英文摘要It is expensive and time-consuming to collect sufficient labeled data for human activity recognition (HAR). Domain adaptation is a promising approach for cross-domain activity recognition. Existing methods mainly focus on adapting cross-domain representations via domain-level, class-level, or sample-level distribution matching. However, they might fail to capture the fine-grained locality information in activity data. The domain-and class-level matching are too coarse that may result in under-adaptation, while sample-level matching may be affected by the noise seriously and eventually cause over-adaptation. In this paper, we propose substructure-level matching for domain adaptation (SSDA) to better utilize the locality information of activity data for accurate and efficient knowledge transfer. Based on SSDA, we propose an optimal transport-based implementation, Substructural Optimal Transport (SOT), for cross domain HAR. We obtain the substructures of activities via clustering methods and seeks the coupling of the weighted substructures between different domains. We conduct comprehensive experiments on four public activity recognition datasets (i.e. UCI-DSADS, UCI-HAR, USC-HAD, PAMAP2), which demonstrates that SOT significantly outperforms other state-of-the-art methods w.r.t classification accuracy (9%+ improvement). In addition, SOT is 5x faster than traditional OT-based DA methods with the same hyper-parameters. (c) 2021 Elsevier B.V. All rights reserved.
资助项目KeyArea Research and Development Program of Guangdong Province[2019B010109001] ; National Natural Science Foundation of China[61972383]
WOS研究方向Computer Science
语种英语
出版者ELSEVIER
WOS记录号WOS:000672469900007
源URL[http://119.78.100.204/handle/2XEOYT63/17526]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Chen, Yiqiang
作者单位1.Microsoft Res Asia, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Lu, Wang,Chen, Yiqiang,Wang, Jindong,et al. Cross-domain activity recognition via substructural optimal transport[J]. NEUROCOMPUTING,2021,454:65-75.
APA Lu, Wang,Chen, Yiqiang,Wang, Jindong,&Qin, Xin.(2021).Cross-domain activity recognition via substructural optimal transport.NEUROCOMPUTING,454,65-75.
MLA Lu, Wang,et al."Cross-domain activity recognition via substructural optimal transport".NEUROCOMPUTING 454(2021):65-75.

入库方式： OAI收割

来源：计算技术研究所

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。