{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T07:16:44Z","timestamp":1781594204513,"version":"3.54.5"},"reference-count":28,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T00:00:00Z","timestamp":1702944000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"RGC","award":["Contract CERG 16204820, 16206122, R6021-20, AoE\/E-601\/22-R, Contract R8015, and 3030_006"],"award-info":[{"award-number":["Contract CERG 16204820, 16206122, R6021-20, AoE\/E-601\/22-R, Contract R8015, and 3030_006"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."],"published-print":{"date-parts":[[2023,12,19]]},"abstract":"<jats:p>Wearable sensor-based human activity recognition (HAR) has gained significant attention due to the widespread use of smart wearable devices. However, variations in different subjects can cause a domain shift that impedes the scaling of the recognition model. Unsupervised domain adaptation has been proposed as a solution to recognize activities in new, unlabeled target domains by training the source and target data together. However, the need for accessing source data raises privacy concerns. Source-free domain adaptation has emerged as a practical setting, where only a pre-trained source model is provided for the unlabeled target domain. This setup aligns with the need for personalized activity model adaptation on target local devices. As the edge devices are resource-constrained with limited memory, it is crucial to take the computational efficiency, i.e., memory cost into consideration. In this paper, we develop a source-free domain adaptation framework for wearable sensor-based HAR, with a focus on computational efficiency for target edge devices. Firstly, we design a lightweight add-on module called adapter to adapt the frozen pre-trained model to the unlabeled target domain. Secondly, to optimize the adapter, we adopt a simple yet effective model adaptation method that leverages local representation similarity and prediction consistency. Additionally, we design a set of sample selection optimization strategies to select samples effective for adaptation and further enhance computational efficiency while maintaining adaptation performance. Our extensive experiments on three datasets demonstrate that our method achieves comparable recognition accuracy to the state-of-the-art source free domain adaptation methods with fewer than 1% of the parameters updated and saves up to 4.99X memory cost.<\/jats:p>","DOI":"10.1145\/3631428","type":"journal-article","created":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T12:52:04Z","timestamp":1705063924000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["SF-Adapter"],"prefix":"10.1145","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3125-0024","authenticated-orcid":false,"given":"Hua","family":"Kang","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8719-7816","authenticated-orcid":false,"given":"Qingyong","family":"Hu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9205-1881","authenticated-orcid":false,"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,1,12]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"crossref","unstructured":"D. Anguita A. Ghio L. Oneto X. Parra and J. L. Reyes-Ortiz. 2012. Human Activity Recognition on Smartphones Using a Multiclass Hardware-Friendly Support Vector Machine. In IWAAL.","DOI":"10.1007\/978-3-642-35395-6_30"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxt075"},{"key":"e_1_2_1_3_1","unstructured":"Han Cai Chuang Gan Ligeng Zhu and Song Han. 2021. TinyTL: Reduce Activations Not Trainable Parameters for Efficient On-Device Learning. arXiv:2007.11622 [cs.CV]"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3380985"},{"key":"e_1_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Yaroslav Ganin Evgeniya Ustinova Hana Ajakan Pascal Germain Hugo Larochelle Fran\u00e7ois Laviolette Mario Marchand and Victor Lempitsky. 2016. Domain-Adversarial Training of Neural Networks. arXiv:1505.07818 [stat.ML]","DOI":"10.1007\/978-3-319-58347-1_10"},{"key":"e_1_2_1_6_1","volume-title":"Parameter-efficient fine-tuning for vision transformers. arXiv preprint arXiv:2203.16329","author":"He Xuehai","year":"2022","unstructured":"Xuehai He, Chunyuan Li, Pengchuan Zhang, Jianwei Yang, and Xin Eric Wang. 2022. Parameter-efficient fine-tuning for vision transformers. arXiv preprint arXiv:2203.16329 (2022)."},{"key":"e_1_2_1_7_1","volume-title":"International Conference on Machine Learning. PMLR, 2790--2799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International Conference on Machine Learning. PMLR, 2790--2799."},{"key":"e_1_2_1_8_1","first-page":"3635","article-title":"Model adaptation: Historical contrastive learning for unsupervised domain adaptation without source data","volume":"34","author":"Huang Jiaxing","year":"2021","unstructured":"Jiaxing Huang, Dayan Guan, Aoran Xiao, and Shijian Lu. 2021. Model adaptation: Historical contrastive learning for unsupervised domain adaptation without source data. Advances in Neural Information Processing Systems 34 (2021), 3635--3649.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOM.2018.8444585"},{"key":"e_1_2_1_10_1","unstructured":"Hang Le Juan Pino Changhan Wang Jiatao Gu Didier Schwab and Laurent Besacier. 2021. Lightweight Adapter Tuning for Multilingual Speech Translation. arXiv:2106.01463 [cs.CL]"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00566"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00966"},{"key":"e_1_2_1_13_1","volume-title":"Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190","author":"Li Xiang Lisa","year":"2021","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)."},{"key":"e_1_2_1_14_1","volume-title":"International Conference on Machine Learning. PMLR, 6028--6039","author":"Liang Jian","year":"2020","unstructured":"Jian Liang, Dapeng Hu, and Jiashi Feng. 2020. Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. In International Conference on Machine Learning. PMLR, 6028--6039."},{"key":"e_1_2_1_15_1","volume-title":"TTN: A domain-shift aware batch normalization in test-time adaptation. arXiv preprint arXiv:2302.05155","author":"Lim Hyesu","year":"2023","unstructured":"Hyesu Lim, Byeonggeun Kim, Jaegul Choo, and Sungha Choi. 2023. TTN: A domain-shift aware batch normalization in test-time adaptation. arXiv preprint arXiv:2302.05155 (2023)."},{"key":"e_1_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Yuang Liu Wei Zhang and Jun Wang. 2021. Source-Free Domain Adaptation for Semantic Segmentation. arXiv:2103.16372 [cs.CV]","DOI":"10.1109\/CVPR46437.2021.00127"},{"key":"e_1_2_1_17_1","volume-title":"Garnett (Eds.)","volume":"31","author":"Long Mingsheng","year":"2018","unstructured":"Mingsheng Long, ZHANGJIE CAO, Jianmin Wang, and Michael I Jordan. 2018. Conditional Adversarial Domain Adaptation. In Advances in Neural Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (Eds.), Vol. 31. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2018\/file\/ab88b15733f543179858600245108dd8-Paper.pdf"},{"key":"e_1_2_1_18_1","volume-title":"UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones. CoRR abs\/1611.07688","author":"Micucci Daniela","year":"2016","unstructured":"Daniela Micucci, Marco Mobilio, and Paolo Napoletano. 2016. UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones. CoRR abs\/1611.07688 (2016). arXiv:1611.07688 http:\/\/arxiv.org\/abs\/1611.07688"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539134"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01147"},{"key":"e_1_2_1_21_1","volume-title":"Tent: Fully test-time adaptation by entropy minimization. arXiv preprint arXiv:2006.10726","author":"Wang Dequan","year":"2020","unstructured":"Dequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno Olshausen, and Trevor Darrell. 2020. Tent: Fully test-time adaptation by entropy minimization. arXiv preprint arXiv:2006.10726 (2020)."},{"key":"e_1_2_1_22_1","volume-title":"TACC: A Full-stack Cloud Computing Infrastructure for Machine Learning Tasks.","author":"Xu Kaiqiang","year":"2021","unstructured":"Kaiqiang Xu, Xinchen Wan, Hao Wang, Zhenghang Ren, Xudong Liao, Decang Sun, Chaoliang Zeng, and Kai Chen. 2021. TACC: A Full-stack Cloud Computing Infrastructure for Machine Learning Tasks."},{"key":"e_1_2_1_23_1","unstructured":"Yuecong Xu Jianfei Yang Haozhi Cao Keyu Wu Wu Min and Zhenghua Chen. 2022. Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition. arXiv:2203.04559 [cs.CV]"},{"key":"e_1_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Shiqi Yang Joost van de Weijer Luis Herranz Shangling Jui et al. 2021. Exploiting the intrinsic neighborhood structure for source-free domain adaptation. Advances in neural information processing systems 34 (2021) 29393--29405.","DOI":"10.1109\/ICCV48922.2021.00885"},{"key":"e_1_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Shiqi Yang Yaxing Wang Joost van de Weijer Luis Herranz and Shangling Jui. 2021. Generalized Source-free Domain Adaptation. arXiv:2108.01614 [cs.CV]","DOI":"10.1109\/ICCV48922.2021.00885"},{"key":"e_1_2_1_26_1","unstructured":"Shiqi Yang Yaxing Wang Kai Wang Shangling Jui et al. 2022. Attracting and dispersing: A simple approach for source-free domain adaptation. In Advances in Neural Information Processing Systems."},{"key":"e_1_2_1_27_1","unstructured":"Ziyi Zhang Weikai Chen Hui Cheng Zhen Li Siyuan Li Liang Lin and Guanbin Li. 2022. Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning. arXiv:2211.06612 [cs.CV]"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544794.3558467"}],"container-title":["Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3631428","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3631428","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T17:00:23Z","timestamp":1756314023000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3631428"}},"subtitle":["Computational-Efficient Source-Free Domain Adaptation for Human Activity Recognition"],"short-title":[],"issued":{"date-parts":[[2023,12,19]]},"references-count":28,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,12,19]]}},"alternative-id":["10.1145\/3631428"],"URL":"https:\/\/doi.org\/10.1145\/3631428","relation":{},"ISSN":["2474-9567"],"issn-type":[{"value":"2474-9567","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,19]]},"assertion":[{"value":"2024-01-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}