Cross-domain activity recognition via substructural optimal transport

NEUROCOMPUTING

卷:454

Article

Lu, Wang^1,2  Chen, Yiqiang^1,2  Wang, Jindong³  Qin, Xin^1,2 

[1] Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China

[2] Univ Chinese Acad Sci, Beijing 100190, Peoples R China

[3] Microsoft Res Asia, Beijing, Peoples R China

关键词: Ubiquitous computing;    Transfer learning;    Domain adaptation;    Optimal transport;    Clustering;   

DOI  :  10.1016/j.neucom.2021.04.124

来源: Elsevier

【 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.

【 授权许可】

Free