Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/182272
Title: ContrastSense: domain-invariant contrastive learning for in-the-wild wearable sensing
Authors: Dai, Gaole
Xu, Huatao
Yoon, Hyungjun
Li, Mo
Tan, Rui
Lee, Sung-Ju
Keywords: Computer and Information Science
Issue Date: 2024
Source: Dai, G., Xu, H., Yoon, H., Li, M., Tan, R. & Lee, S. (2024). ContrastSense: domain-invariant contrastive learning for in-the-wild wearable sensing. Proceedings of the ACM On Interactive, Mobile, Wearable and Ubiquitous Technologies, 8(4), 3699744-. https://dx.doi.org/10.1145/3699744
Project: MOE-T2EP20220-0004
Journal: Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Abstract: Existing wearable sensing models often struggle with domain shifts and class label scarcity. Contrastive learning is a promising technique to address class label scarcity, which however captures domain-related features and suffers from low-quality negatives. To address both problems, we propose ContrastSense, a domain-invariant contrastive learning scheme for a realistic wearable sensing scenario where domain shifts and class label scarcity are presented simultaneously. To capture domain-invariant information, ContrastSense exploits unlabeled data and domain labels specifying user IDs or devices to minimize the discrepancy across domains. To improve the quality of negatives, time and domain labels are leveraged to select samples and refine negatives. In addition, ContrastSense designs a parameter-wise penalty to preserve domaininvariant knowledge during fine-tuning to further maintain model robustness. Extensive experiments show that ContrastSense outperforms the state-of-the-art baselines by 8.9% on human activity recognition with inertial measurement units and 5.6% on gesture recognition with electromyography when presented with domain shifts across users. Besides, when presented with different kinds of domain shifts across devices, on-body positions, and datasets, ContrastSense achieves consistent improvements compared with the best baselines.
URI: https://hdl.handle.net/10356/182272
ISSN: 2474-9567
DOI: 10.1145/3699744
Schools: College of Computing and Data Science 
Rights: © 2024 the Owner/Author(s). This work is licensed under a Creative Commons Attribution International 4.0 License.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:CCDS Journal Articles

Files in This Item:
File Description SizeFormat 
3699744.pdf1.43 MBAdobe PDFView/Open

Page view(s)

74
Updated on Feb 16, 2025

Download(s)

10
Updated on Feb 16, 2025

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.