{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:03Z","timestamp":1750309503232,"version":"3.41.0"},"reference-count":48,"publisher":"Association for Computing Machinery (ACM)","issue":"11","license":[{"start":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T00:00:00Z","timestamp":1731456000000},"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","doi-asserted-by":"crossref","award":["61932007, 61972013, 62141209"],"award-info":[{"award-number":["61932007, 61972013, 62141209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Guangxi Collaborative Innovation Center of Multi-source Information Integration and Intelligent Processing and partly by JSPS KAKENHI","award":["23H03402"],"award-info":[{"award-number":["23H03402"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2024,11,30]]},"abstract":"<jats:p>\n            Unsupervised multi-class domain adaptation (multi-class UDA) has recently been proposed to fill the gap between empirically practical methods for multi-class classification and well-founded theory with the setting of binary classification. Nevertheless, the multi-class UDA methods use model predictions to characterize the disagreement of multi-class scoring hypotheses, which is used to optimize the divergence between domain distributions. Such self-training manner may bring inaccurate model predictions, which would damage the target structure due to the absence of labels of the target domain, leading to sub-optimal performance. On the other hand, this disagreement between multi-class scoring hypotheses does not involve the relationships among all of the multiple classes. It causes that multi-class UDA cannot properly connect the advanced practical UDA methods that consider class-conditional distribution alignment. Thus, we propose to exploit the target structure information and then incorporate it into multi-class UDA to achieve class-conditional distribution alignment. We theoretically and experimentally explain the importance of accurate target structure information to reduce the expected error on the target domain. Notably, our method achieves state-of-the-art results on three commonly-used benchmarks with different scales. In addition, using the target structure information, we propose a variant to cope with noisy open-world source domains such as noisy labels and out-of-distribution samples, enhancing the robustness of our method. The source code is available at\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"url\" xlink:href=\"https:\/\/github.com\/jingzhengli\/Multi_Class_UDA\">https:\/\/github.com\/jingzhengli\/Multi_Class_UDA<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3686156","type":"journal-article","created":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T13:22:06Z","timestamp":1722691326000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Target Structure Learning Framework for Unsupervised Multi-Class Domain Adaptation"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4232-8798","authenticated-orcid":false,"given":"Jingzheng","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, China and Zhongguancun Laboratory, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7654-5574","authenticated-orcid":false,"given":"Hailong","family":"Sun","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Complex and Critical Software Environment (CCSE) and Hangzhou Innovation Institute, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2110-838X","authenticated-orcid":false,"given":"Lei","family":"Chai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4997-3850","authenticated-orcid":false,"given":"Jiyi","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Yamanashi, Yamanashi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,13]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5152-4"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475496"},{"key":"e_1_3_3_4_2","first-page":"1416","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Cicek Safa","year":"2019","unstructured":"Safa Cicek and Stefano Soatto. 2019. Unsupervised domain adaptation via regularized conditional alignment. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. IEEE Computer Society, Piscataway, NJ, 1416\u20131425."},{"key":"e_1_3_3_5_2","first-page":"3937","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Du Zhekai","year":"2021","unstructured":"Zhekai Du, Jingjing Li, Hongzu Su, Lei Zhu, and Ke Lu. 2021. Cross-domain gradient discrepancy minimization for unsupervised domain adaptation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, Piscataway, NJ, 3937\u20133946."},{"key":"e_1_3_3_6_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"French Geoff","year":"2018","unstructured":"Geoff French, Michal Mackiewicz, and Mark Fisher. 2018. Self-ensembling for visual domain adaptation. In Proceedings of the International Conference on Learning Representations. OpenReview.net, Washington, DC."},{"key":"e_1_3_3_7_2","first-page":"1180","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Ganin Yaroslav","year":"2015","unstructured":"Yaroslav Ganin and Victor Lempitsky. 2015. Unsupervised domain adaptation by backpropagation. In Proceedings of the International Conference on Machine Learning. PMLR, ACM, New York, NY, 1180\u20131189."},{"key":"e_1_3_3_8_2","first-page":"1","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin Yaroslav","year":"2016","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. Journal of Machine Learning Research 17 (2016), 1\u201335.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109088"},{"key":"e_1_3_3_10_2","first-page":"11721","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hoyer Lukas","year":"2023","unstructured":"Lukas Hoyer, Dengxin Dai, Haoran Wang, and Luc Van Gool. 2023. MIC: Masked image consistency for context-enhanced domain adaptation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, Piscataway, NJ, 11721\u201311732."},{"key":"e_1_3_3_11_2","first-page":"1203","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Huang Jiaxing","year":"2022","unstructured":"Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu, and Ling Shao. 2022. Category contrast for unsupervised domain adaptation in visual tasks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, Piscataway, NJ, 1203\u20131214."},{"key":"e_1_3_3_12_2","first-page":"464","volume-title":"European Conference on Computer Vision","author":"Jin Ying","year":"2020","unstructured":"Ying Jin, Ximei Wang, Mingsheng Long, and Jianmin Wang. 2020. Minimum class confusion for versatile domain adaptation. In European Conference on Computer Vision. Springer, Berlin, 464\u2013480."},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00503"},{"key":"e_1_3_3_14_2","first-page":"11","article-title":"Maximum density divergence for domain adaptation","volume":"43","author":"Li Jingjing","year":"2021","unstructured":"Jingjing Li, Erpeng Chen, Zhengming Ding, Lei Zhu, Ke Lu, and Heng Tao Shen. 2021. Maximum density divergence for domain adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence 43, 11 (2021), 3918\u20133930.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107123"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3468673"},{"key":"e_1_3_3_17_2","first-page":"351","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Lin Hongbin","year":"2022","unstructured":"Hongbin Lin, Yifan Zhang, Zhen Qiu, Shuaicheng Niu, Chuang Gan, Yanxia Liu, and Mingkui Tan. 2022. Prototype-guided continual adaptation for class-incremental unsupervised domain adaptation. In Proceedings of the European Conference on Computer Vision. Springer, Berlin, 351\u2013368."},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.5555\/3326943.3327094"},{"key":"e_1_3_3_19_2","first-page":"2208","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Long Mingsheng","year":"2017","unstructured":"Mingsheng Long, Han Zhu, Jianmin Wang, and Michael I. Jordan. 2017. Deep transfer learning with joint adaptation networks. In Proceedings of the International Conference on Machine Learning. PMLR, ACM, New York, NY, 2208\u20132217."},{"key":"e_1_3_3_20_2","volume-title":"Proceedings of the 22nd Conference on Learning Theory (COLT \u201909)","author":"Mansour Yishay","year":"2009","unstructured":"Yishay Mansour, Mehryar Mohri, and Afshin Rostamizadeh. 2009. Domain adaptation: Learning bounds and algorithms. In Proceedings of the 22nd Conference on Learning Theory (COLT \u201909). Springer, Berlin."},{"key":"e_1_3_3_21_2","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Mattia Litrico","year":"2023","unstructured":"Litrico Mattia, Del Bue Alessio, and Morerio Pietro. 2023. Guiding pseudo-labels with uncertainty estimation for source-free unsupervised domain adaptation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, Piscataway, NJ."},{"key":"e_1_3_3_22_2","volume-title":"Proceedings of the Workshop of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Peng Xingchao","year":"2018","unstructured":"Xingchao Peng, Ben Usman, Neela Kaushik, Judy Hoffman, Dequan Wang, and Kate Saenko. 2018. Visda: The visual domain adaptation challenge. In Proceedings of the Workshop of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, Piscataway, NJ."},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_16"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00392"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11784"},{"key":"e_1_3_3_26_2","article-title":"Prototypical networks for few-shot learning","author":"Snell Jake","year":"2017","unstructured":"Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. In Proceedings of the Advances in Neural Information Processing Systems.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_27_2","first-page":"596","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","volume":"33","author":"Sohn Kihyuk","year":"2020","unstructured":"Kihyuk Sohn, David Berthelot, Nicholas Carlini, Zizhao Zhang, Han Zhang, Colin A. Raffel, Ekin Dogus Cubuk, Alexey Kurakin, and Chun-Liang Li. 2020. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Advances in Neural Information Processing Systems 33 (2020), 596\u2013608.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00705"},{"key":"e_1_3_3_29_2","first-page":"8725","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Tang Hui","year":"2020","unstructured":"Hui Tang, Ke Chen, and Kui Jia. 2020. Unsupervised domain adaptation via structurally regularized deep clustering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, Piscataway, NJ, 8725\u20138735."},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108638"},{"issue":"10","key":"e_1_3_3_31_2","doi-asserted-by":"crossref","first-page":"6517","DOI":"10.1109\/TPAMI.2021.3087830","article-title":"Towards uncovering the intrinsic data structures for unsupervised domain adaptation using structurally regularized deep clustering","volume":"44","author":"Tang Hui","year":"2021","unstructured":"Hui Tang, Xiatian Zhu, Ke Chen, Kui Jia, and C. L. Philip Chen. 2021. Towards uncovering the intrinsic data structures for unsupervised domain adaptation using structurally regularized deep clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 10 (2021), 6517\u20136533.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.572"},{"key":"e_1_3_3_33_2","first-page":"6243","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"34","author":"Wang Qian","year":"2020","unstructured":"Qian Wang and Toby Breckon. 2020. Unsupervised domain adaptation via structured prediction based selective pseudo-labeling. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. AAAI, Menlo Park, CA, 6243\u20136250."},{"key":"e_1_3_3_34_2","article-title":"Cross-domain contrastive learning for unsupervised domain adaptation","author":"Wang Rui","year":"2022","unstructured":"Rui Wang, Zuxuan Wu, Zejia Weng, Jingjing Chen, Guo-Jun Qi, and Yu-Gang Jiang. 2022. Cross-domain contrastive learning for unsupervised domain adaptation. IEEE Transactions on Multimedia (2022).","journal-title":"IEEE Transactions on Multimedia"},{"key":"e_1_3_3_35_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Wang Yisen","year":"2019","unstructured":"Yisen Wang, Difan Zou, Jinfeng Yi, James Bailey, Xingjun Ma, and Quanquan Gu. 2019. Improving adversarial robustness requires revisiting misclassified examples. In Proceedings of the International Conference on Learning Representations. OpenReview.net, Washington DC."},{"key":"e_1_3_3_36_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Wiles Olivia","year":"2022","unstructured":"Olivia Wiles, Sven Gowal, Florian Stimberg, Sylvestre Alvise-Rebuffi, Ira Ktena, Krishnamurthy Dvijotham, and Taylan Cemgil. 2022. A fine-grained analysis on distribution shift. In Proceedings of the International Conference on Learning Representations (2022)."},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3486251"},{"key":"e_1_3_3_38_2","article-title":"Entropy minimization versus diversity maximization for domain adaptation","author":"Wu Xiaofu","year":"2021","unstructured":"Xiaofu Wu, Suofei Zhang, Quan Zhou, Zhen Yang, Chunming Zhao, and Longin Jan Latecki. 2021. Entropy minimization versus diversity maximization for domain adaptation. IEEE Transactions on Neural Networks and Learning Systems (2021).","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_3_39_2","first-page":"5423","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Xie Shaoan","year":"2018","unstructured":"Shaoan Xie, Zibin Zheng, Liang Chen, and Chuan Chen. 2018. Learning semantic representations for unsupervised domain adaptation. In Proceedings of the International Conference on Machine Learning. PMLR, ACM, New York, NY, 5423\u20135432."},{"key":"e_1_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00151"},{"key":"e_1_3_3_41_2","volume-title":"Proceedings or the International Conference on Learning Representations","author":"Xu Tongkun","year":"2022","unstructured":"Tongkun Xu, Weihua Chen, WANG Pichao, Fan Wang, Hao Li, and Rong Jin. 2022. CDTrans: Cross-domain transformer for unsupervised domain adaptation. In Proceedings or the International Conference on Learning Representations. OpenReview.net, Washington DC."},{"key":"e_1_3_3_42_2","article-title":"MixOOD: Improving out-of-distribution detection with enhanced data mixup","author":"Yang Taocun","year":"2023","unstructured":"Taocun Yang, Yaping Huang, Yanlin Xie, Junbo Liu, and Shengchun Wang. 2023. MixOOD: Improving out-of-distribution detection with enhanced data mixup. ACM Transactions on Multimedia Computing, Communications and Applications (2023).","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01362"},{"key":"e_1_3_3_44_2","article-title":"Unsupervised multi-class domain adaptation: Theory, algorithms, and practice","author":"Zhang Yabin","year":"2020","unstructured":"Yabin Zhang, Bin Deng, Hui Tang, Lei Zhang, and Kui Jia. 2020. Unsupervised multi-class domain adaptation: Theory, algorithms, and practice. IEEE Transactions on Pattern Analysis and Machine Intelligence (2020).","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_3_45_2","first-page":"7404","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Zhang Yuchen","year":"2019","unstructured":"Yuchen Zhang, Tianle Liu, Mingsheng Long, and Michael Jordan. 2019. Bridging theory and algorithm for domain adaptation. In Proceedings of the International Conference on Machine Learning. PMLR, ACM, New York, NY, 7404\u20137413."},{"key":"e_1_3_3_46_2","first-page":"5031","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Zhang Yabin","year":"2019","unstructured":"Yabin Zhang, Hui Tang, Kui Jia, and Mingkui Tan. 2019. Domain-symmetric networks for adversarial domain adaptation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, Piscataway, NJ, 5031\u20135040."},{"key":"e_1_3_3_47_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Zhang Yikai","year":"2021","unstructured":"Yikai Zhang, Songzhu Zheng, Pengxiang Wu, Mayank Goswami, and Chao Chen. 2021. Learning with feature-dependent label noise: A progressive approach. In Proceedings of the International Conference on Learning Representations. OpenReview.net, Washington, DC."},{"key":"e_1_3_3_48_2","first-page":"7523","volume-title":"International Conference on Machine Learning","author":"Zhao Han","year":"2019","unstructured":"Han Zhao, Remi Tachet Des Combes, Kun Zhang, and Geoffrey Gordon. 2019. On learning invariant representations for domain adaptation. In International Conference on Machine Learning. PMLR, ACM, New York, NY, 7523\u20137532."},{"key":"e_1_3_3_49_2","article-title":"A review of single-source deep unsupervised visual domain adaptation","author":"Zhao Sicheng","year":"2020","unstructured":"Sicheng Zhao, Xiangyu Yue, Shanghang Zhang, Bo Li, Han Zhao, Bichen Wu, Ravi Krishna, Joseph E. Gonzalez, Alberto L. Sangiovanni-Vincentelli, Sanjit A. Seshia, and Kurt Keutzer. 2020. A review of single-source deep unsupervised visual domain adaptation. IEEE Transactions on Neural Networks and Learning Systems (2020).","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3686156","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3686156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:50Z","timestamp":1750295870000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3686156"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,13]]},"references-count":48,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,11,30]]}},"alternative-id":["10.1145\/3686156"],"URL":"https:\/\/doi.org\/10.1145\/3686156","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"type":"print","value":"1551-6857"},{"type":"electronic","value":"1551-6865"}],"subject":[],"published":{"date-parts":[[2024,11,13]]},"assertion":[{"value":"2023-05-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-07-21","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}