{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:35:21Z","timestamp":1767339321868,"version":"3.41.0"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2021,11,12]],"date-time":"2021-11-12T00:00:00Z","timestamp":1636675200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62172420, 61672523"],"award-info":[{"award-number":["62172420, 61672523"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Beijing Natural Science Foundation","award":["4202033"],"award-info":[{"award-number":["4202033"]}]},{"name":"Fundamental Research Funds for the Central Universities and the Research Funds of Renmin University of China","award":["18XNLG19"],"award-info":[{"award-number":["18XNLG19"]}]},{"name":"Pharmaceutical Collaborative Innovation Research Project of Beijing Science and Technology Commission","award":["Z191100007719002"],"award-info":[{"award-number":["Z191100007719002"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2021,11,30]]},"abstract":"<jats:p>Expanding visual categorization into a novel domain without the need of extra annotation has been a long-term interest for multimedia intelligence. Previously, this challenge has been approached by unsupervised domain adaptation (UDA). Given labeled data from a source domain and unlabeled data from a target domain, UDA seeks for a deep representation that is both discriminative and domain-invariant. While UDA focuses on the target domain, we argue that the performance on both source and target domains matters, as in practice which domain a test example comes from is unknown. In this article, we extend UDA by proposing a new task called unsupervised domain expansion (UDE), which aims to adapt a deep model for the target domain with its unlabeled data, meanwhile maintaining the model\u2019s performance on the source domain. We propose Knowledge Distillation Domain Expansion (KDDE) as a general method for the UDE task. Its domain-adaptation module can be instantiated with any existing model. We develop a knowledge distillation-based learning mechanism, enabling KDDE to optimize a single objective wherein the source and target domains are equally treated. Extensive experiments on two major benchmarks, i.e.,\u00a0Office-Home and DomainNet, show that KDDE compares favorably against four competitive baselines, i.e.,\u00a0DDC, DANN, DAAN, and CDAN, for both UDA and UDE tasks. Our study also reveals that the current UDA models improve their performance on the target domain at the cost of noticeable performance loss on the source domain.<\/jats:p>","DOI":"10.1145\/3448108","type":"journal-article","created":{"date-parts":[[2021,11,12]],"date-time":"2021-11-12T21:16:06Z","timestamp":1636751766000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Unsupervised Domain Expansion for Visual Categorization"],"prefix":"10.1145","volume":"17","author":[{"given":"Jie","family":"Wang","sequence":"first","affiliation":[{"name":"Key Lab of DEKE, Renmin University of China, Beijing, China"}]},{"given":"Kaibin","family":"Tian","sequence":"additional","affiliation":[{"name":"Key Lab of DEKE, Renmin University of China, Beijing, China"}]},{"given":"Dayong","family":"Ding","sequence":"additional","affiliation":[{"name":"Vistel AI Lab, Visionary Intelligence Ltd. Beijing, Beijing, China"}]},{"given":"Gang","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China"}]},{"given":"Xirong","family":"Li","sequence":"additional","affiliation":[{"name":"Key Lab of DEKE, Renmin University of China, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2021,11,12]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953145"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.5555\/2976456.2976474"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294842"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0107-6"},{"key":"e_1_3_2_6_2","volume-title":"Proceedings of the CVPR","author":"Duan Lixin","year":"2009","unstructured":"Lixin Duan, Ivor W. Tsang, Dong Xu, and Stephen J. Maybank. 2009. Domain Transfer SVM for video concept detection. In Proceedings of the CVPR."},{"key":"e_1_3_2_7_2","volume-title":"Proceedings of the ICLR","author":"French, Michal Mackiewicz, Geoffrey","year":"2018","unstructured":"Michal Mackiewicz, Geoffrey French, and Mark Fisher. 2018. Self-ensembling for visual domain adaptation. In Proceedings of the ICLR."},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946704"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5816"},{"key":"e_1_3_2_10_2","volume-title":"Proceedings of the NIPS Deep Learning Workshop","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeffrey Dean. 2015. Distilling the Knowledge in a Neural Network. In Proceedings of the NIPS Deep Learning Workshop."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2008.4711716"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00503"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2018.02.010"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351070"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00271"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045130"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.5555\/3326943.3327094"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.5555\/3305890.3305909"},{"key":"e_1_3_2_19_2","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten Laurens van der","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. J. Mach. Learn. Res. 9(Nov.2008), 2579\u20132605.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003776"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461682"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00835"},{"key":"e_1_3_2_26_2","article-title":"FitNets: Hints for thin deep nets","author":"Romero Adriana","year":"2015","unstructured":"Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2015. FitNets: Hints for thin deep nets. Proceedings of the ICLR (2015).","journal-title":"Proceedings of the ICLR"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00814"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00392"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00035"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683533"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"e_1_3_2_33_2","article-title":"Contrastive representation distillation","author":"Tian Yonglong","year":"2020","unstructured":"Yonglong Tian, Dilip Krishnan, and Phillip Isola. 2020. Contrastive representation distillation. In Proceedings of the ICLR.","journal-title":"Proceedings of the ICLR"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.3390\/technologies8020035"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"e_1_3_2_36_2","article-title":"Deep Domain Confusion: Maximizing for Domain Invariance","author":"Tzeng Eric","year":"2014","unstructured":"Eric Tzeng, Judy Hoffman, Ning Zhang, Kate Saenko, and Trevor Darrell. 2014. Deep Domain Confusion: Maximizing for Domain Invariance. Retrieved from https:\/\/ArXivabs\/1412.3474.","journal-title":"Retrieved from https:\/\/ArXivabs\/1412.3474"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.572"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32239-7_18"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454462"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015345"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291276"},{"key":"e_1_3_2_42_2","volume-title":"Proceedings of the ICCV","author":"Yu Xiaofeng Liu, B. V. K. Vijaya, Kumar Jinsong, Wang Yang Zou, and Zhiding","year":"2019","unstructured":"Xiaofeng Liu, B. V. K. Vijaya, Kumar Jinsong, Wang Yang Zou, and Zhiding Yu. 2019. Confidence regularized self-training. In Proceedings of the ICCV."},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00088"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351089"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.5555\/3504035.3504582"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_18"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3448108","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3448108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:24:59Z","timestamp":1750195499000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3448108"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,12]]},"references-count":47,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,11,30]]}},"alternative-id":["10.1145\/3448108"],"URL":"https:\/\/doi.org\/10.1145\/3448108","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"type":"print","value":"1551-6857"},{"type":"electronic","value":"1551-6865"}],"subject":[],"published":{"date-parts":[[2021,11,12]]},"assertion":[{"value":"2020-07-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-01-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}