{"type":"ScholarlyArticle","title":"Rethinking Correlation Learning via Label Prior for Open Set Domain Adaptation","authors":[{"name":"Zi-Xian Huang","slug":"zi-xian-huang","given":"Zi-Xian","family":"Huang","affiliation":"School of Mathematics , Sun Yat-Sen University , China"},{"name":"Chuan-Xian Ren","slug":"chuan-xian-ren","given":"Chuan-Xian","family":"Ren","affiliation":"School of Mathematics , Sun Yat-Sen University , China"}],"abstract":"Open Set Domain Adaptation (OSDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain, where known classes exist across domains while unknown classes are present only in the target domain. Existing methods rely on the clustering structure to identify the unknown classes, which empirically induces a large identification error if the unknown classes are a mixture of multiple components. To break through this barrier, we formulate OSDA from the view of correlation and propose a correlation metric-based framework called Balanced Correlation Learning (BCL). BCL employs Hilbert-Schmidt Independence Criterion (HSIC) to characterize the separation between unknown and known classes, where HSIC is reformulated as the nodes’ relation on graph. By considering the label prior as variable, theoretical results are derived to analytically show a sufficient condition for desired learning direction for OSDA. Methodologically, the class-balanced HSIC is proposed to preserve domain-invariant and class-discriminative features. With the guarantee of correlation learning, the entropy-based principle can effectively identify the unknown classes via uncertainty. Empirically, extensive evaluations are conducted, where BCL achieves significant performance improvements.","doi":"10.24963/ijcai.2024/98","url":"https://ijcai.org/proceedings/2024/98","pdf":"https://ijcai.org/proceedings/2024/0098.pdf","markdown":"https://ijcai.org/proceedings/2024/98.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/98","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Computer Vision","track":"Main Track","number":98,"pages":{"first":884,"last":892},"keywords":["Computer Vision: CV: Transfer, low-shot, semi- and un- supervised learning","Computer Vision: CV: Machine learning for vision"],"videos":[],"references":[{"position":1,"raw":"[Bucci et al., 2020] Silvia Bucci, Mohammad Reza Logh- mani, and Tatiana Tommasi. On the effectiveness of image rotation for open set domain adaptation. In European Con- ference on Computer Vision, pages 422-438, 2020.","title":"On the effectiveness of image rotation for open set domain adaptation","authors":"Silvia Bucci, Mohammad, Reza Loghmani, Tatiana Tommasi","year":"2020","venue":"European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Fang et al., 2020] Zhen Fang, Jie Lu, Feng Liu, Junyu Xuan, and Guangquan Zhang. Open set domain adapta- tion: Theoretical bound and algorithm. IEEE Transactions on Neural Networks and Learning Systems, 32(10):4309- 4322, 2020.","title":"Open set domain adaptation: Theoretical bound and algorithm","authors":"Zhen Fang, Jie Lu, Feng Liu, Junyu Xuan, Guangquan Zhang","year":"2020","venue":"IEEE Transactions on Neural Networks and Learning Systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Fukumizu et al., 2007] Kenji Fukumizu, Arthur Gretton, Xiaohai Sun, and Bernhard Schölkopf. Kernel measures of conditional dependence. Advances in Neural Informa- tion Processing Systems, 20, 2007.","title":"Kernel measures of conditional dependence","authors":"Kenji Fukumizu, Arthur Gretton, Xiaohai Sun, Bernhard Schölkopf","year":"2007","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Ganin and Lempitsky, 2015] Yaroslav Ganin and Victor Lempitsky. Unsupervised domain adaptation by backprop- agation. In International conference on machine learning, pages 1180-1189, 2015.","title":"Unsupervised domain adaptation by backpropagation","authors":"Yaroslav Ganin, Victor Lempitsky","year":"2015","venue":"International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Gretton et al., 2005] Arthur Gretton, Olivier Bousquet, Alex Smola, and Bernhard Schölkopf. Measuring statis- tical dependence with hilbert-schmidt norms. In Interna- tional Conference on Algorithmic Learning Theory, pages 63-77, 2005.","title":"Measuring statistical dependence with hilbert-schmidt norms","authors":"Arthur Gretton, Olivier Bousquet, Alex Smola, Bernhard Schölkopf","year":"2005","venue":"International Conference on Algorithmic Learning Theory","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[He and Niyogi, 2003] Xiaofei He and Partha Niyogi. Lo- cality preserving projections. Advances in Neural Infor- mation Processing Systems, 16, 2003.","title":"Locality preserving projections","authors":"Xiaofei He, Partha Niyogi","year":"2003","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Jang et al., 2022] JoonHo Jang, Byeonghu Na, Dong Hyeok Shin, Mingi Ji, Kyungwoo Song, and Il-Chul Moon. Unknown-aware domain adversarial learning for open-set domain adaptation. Advances in Neural Information Pro- cessing Systems, 35:16755-16767, 2022.","title":"Unknown-aware domain adversarial learning for open-set domain adaptation","authors":"Jang","year":"2022","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Jing et al., 2021] Mengmeng Jing, Jingjing Li, Lei Zhu, Zhengming Ding, Ke Lu, and Yang Yang. Balanced open set domain adaptation via centroid alignment. In Pro- ceedings of the AAAI Conference on Artificial Intelligence, pages 8013-8020, 2021.","title":"Balanced open set domain adaptation via centroid alignment","authors":"Mengmeng Jing, Jingjing Li, Lei Zhu, Zhengming Ding, Ke Lu, Yang Yang","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kundu et al., 2020] Jogendra Nath Kundu, Naveen Venkat, Ambareesh Revanur, R Venkatesh Babu, et al. Towards in- heritable models for open-set domain adaptation. In Pro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12376-12385, 2020.","title":"Towards inheritable models for open-set domain adaptation","authors":"Kundu","year":"2020","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Li et al., 2023] Wuyang Li, Jie Liu, Bo Han, and Yixuan Yuan. Adjustment and alignment for unbiased open set do- main adaptation. In Proceedings of the IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition, pages 24110-24119, 2023.","title":"Adjustment and alignment for unbiased open set domain adaptation","authors":"Wuyang Li, Jie Liu, Bo Han, Yixuan Yuan","year":"2023","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Liu et al., 2019] Hong Liu, Zhangjie Cao, Mingsheng Long, Jianmin Wang, and Qiang Yang. Separate to adapt: Open set domain adaptation via progressive separation. In Proceedings of the IEEE/CVF Conference on computer vi- sion and Pattern Recognition, pages 2927-2936, 2019.","title":"Separate to adapt: Open set domain adaptation via progressive separation","authors":"Liu","year":"2019","venue":"Proceedings of the IEEE/CVF Conference on computer vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Liu et al., 2023] Jieyan Liu, Hongcai He, Mingzhu Liu, Jingjing Li, and Ke Lu. Manifold regularized joint trans- fer for open set domain adaptation. IEEE Transactions on Multimedia, 2023.","title":"Manifold regularized joint transfer for open set domain adaptation","authors":"Liu","year":"2023","venue":"IEEE Transactions on Multimedia","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Long et al., 2013] Mingsheng Long, Jianmin Wang, Guiguang Ding, Jiaguang Sun, and Philip S Yu. Transfer feature learning with joint distribution adaptation. In Proceedings of the IEEE International Conference on Computer Vision, pages 2200-2207, 2013.","title":"Transfer feature learning with joint distribution adaptation","authors":"Mingsheng Long, Jianmin Wang, Guiguang Ding, Jiaguang Sun, Philip S Yu","year":"2013","venue":"Proceedings of the IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Luo et al., 2020] Yadan Luo, Zijian Wang, Zi Huang, and Mahsa Baktashmotlagh. Progressive graph learning for open-set domain adaptation. In International Conference on Machine Learning, pages 6468-6478, 2020.","title":"Progressive graph learning for open-set domain adaptation","authors":"Yadan Luo, Zijian Wang, Zi Huang, Mahsa Baktashmotlagh","year":"2020","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Ma et al., 2020] Wan-Duo Kurt Ma, JP Lewis, and W Bas- tiaan Kleijn. The hsic bottleneck: Deep learning without back-propagation. In Proceedings of the AAAI conference on artificial intelligence, pages 5085-5092, 2020.","title":"The hsic bottleneck: Deep learning without back-propagation","authors":"Wan-Duo Kurt Ma, J P Lewis, W Bastiaan Kleijn","year":"2020","venue":"Proceedings of the AAAI conference on artificial intelligence","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Pan et al., 2020] Yingwei Pan, Ting Yao, Yehao Li, Chong- Wah Ngo, and Tao Mei. Exploring category-agnostic clus- ters for open-set domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition, pages 13867-13875, 2020.","title":"Exploring category-agnostic clusters for open-set domain adaptation","authors":"Pan","year":"2020","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Panareda Busto and Gall, 2017] Pau Panareda Busto and Juergen Gall. Open set domain adaptation. In Proceed- ings of the IEEE International Conference on Computer Vision, pages 754-763, 2017.","title":"Open set domain adaptation","authors":"Panareda Busto, ; Gall, Panareda Pau, Juergen Busto, Gall","year":"2017","venue":"Proceedings of the IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Peng et al., 2017] Xingchao Peng, Ben Usman, Neela Kaushik, Judy Hoffman, Dequan Wang, and Kate Saenko. Visda: The visual domain adaptation challenge. arXiv preprint arXiv:1710.06924, 2017.","title":"Visda: The visual domain adaptation challenge","authors":"Peng","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Qu et al., 2023] Sanqing Qu, Tianpei Zou, Florian Röhrbein, Cewu Lu, Guang Chen, Dacheng Tao, and Changjun Jiang. Upcycling models under domain and category shift. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 20019-20028, 2023.","title":"Upcycling models under domain and category shift","authors":"Sanqing Qu, Tianpei Zou, Florian Röhrbein, Cewu Lu, Guang Chen, Dacheng Tao, Changjun Jiang","year":"2023","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Saenko et al., 2010] Kate Saenko, Brian Kulis, Mario Fritz, and Trevor Darrell. Adapting visual category models to new domains. In Computer Vision-ECCV 2010: 11th Eu- ropean Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part IV 11, pages 213-226, 2010.","title":"Adapting visual category models to new domains","authors":"Saenko","year":"2010","venue":"Computer Vision-ECCV 2010: 11th European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Saito et al., 2018] Kuniaki Saito, Shohei Yamamoto, Yoshi- taka Ushiku, and Tatsuya Harada. Open set domain adap- tation by backpropagation. In Proceedings of the Eu- ropean Conference on Computer Vision, pages 153-168, 2018.","title":"Open set domain adaptation by backpropagation","authors":"Kuniaki Saito, Shohei Yamamoto, Yoshitaka Ushiku, Tatsuya Harada","year":"2018","venue":"Proceedings of the European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Saito et al., 2020] Kuniaki Saito, Donghyun Kim, Stan Sclaroff, and Kate Saenko. Universal domain adaptation through self supervision. Advances in Neural Information Processing Systems, 33:16282-16292, 2020.","title":"Universal domain adaptation through self supervision","authors":"Kuniaki Saito, Donghyun Kim, Stan Sclaroff, Kate Saenko","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Scheirer et al., 2012] Walter J Scheirer, Anderson de Rezende Rocha, Archana Sapkota, and Terrance E Boult. Toward open set recognition. IEEE Transac- tions on Pattern Analysis and Machine Intelligence, 35(7):1757-1772, 2012.","title":"Toward open set recognition","authors":"J Walter, Anderson Scheirer, De Rezende, Archana Rocha, Terrance E Sapkota, Boult","year":"2012","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Seidenfeld, 1987] Teddy Seidenfeld. Entropy and uncer- tainty. Foundations of statistical inference, pages 259- 287, 1987.","title":"Teddy Seidenfeld. Entropy and uncertainty","authors":"Seidenfeld","year":"1987","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Shermin et al., 2020] Tasfia Shermin, Guojun Lu, Shyh Wei Teng, Manzur Murshed, and Ferdous Sohel. Adversar- ial network with multiple classifiers for open set domain adaptation. IEEE Transactions on Multimedia, 23:2732- 2744, 2020.","title":"Adversarial network with multiple classifiers for open set domain adaptation","authors":"Shermin","year":"2020","venue":"IEEE Transactions on Multimedia","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Tishby et al., 2000] Naftali Tishby, Fernando C Pereira, and William Bialek. The information bottleneck method. arXiv preprint physics/0004057, 2000.","title":"The information bottleneck method","authors":"Naftali Tishby, Fernando C Pereira, William Bialek","year":"2000","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Venkateswara et al., 2017] Hemanth Venkateswara, Jose Eusebio, Shayok Chakraborty, and Sethuraman Pan- chanathan. Deep hashing network for unsupervised do- main adaptation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5018- 5027, 2017.","title":"Deep hashing network for unsupervised domain adaptation","authors":"Hemanth Venkateswara, Jose Eusebio, Shayok Chakraborty, Sethuraman Panchanathan","year":"2017","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Wang et al., 2021a] Qian Wang, Fanlin Meng, and Toby P Breckon. Progressively select and reject pseudo-labelled samples for open-set domain adaptation. arXiv preprint arXiv:2110.12635, 2021.","title":"Progressively select and reject pseudo-labelled samples for open-set domain adaptation","authors":"Wang","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Wang et al., 2021b] Wei Wang, Haojie Li, Zhengming Ding, Feiping Nie, Junyang Chen, Xiao Dong, and Zhi- hui Wang. Rethinking maximum mean discrepancy for visual domain adaptation. IEEE Transactions on Neural Networks and Learning Systems, 2021.","title":"Rethinking maximum mean discrepancy for visual domain adaptation","authors":"Wang","year":"2021","venue":"IEEE Transactions on Neural Networks and Learning Systems","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Xu et al., 2019] Ruijia Xu, Guanbin Li, Jihan Yang, and Liang Lin. Larger norm more transferable: An adaptive feature norm approach for unsupervised domain adapta- tion. In Proceedings of the IEEE/CVF International Con- ference on Computer Vision, pages 1426-1435, 2019.","title":"Larger norm more transferable: An adaptive feature norm approach for unsupervised domain adaptation","authors":"Xu","year":"2019","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Yan et al., 2017] Ke Yan, Lu Kou, and David Zhang. Learn- ing domain-invariant subspace using domain features and independence maximization. IEEE Transactions on Cy- bernetics, 48(1):288-299, 2017.","title":"Learning domain-invariant subspace using domain features and independence maximization","authors":"Ke Yan, Lu Kou, David Zhang","year":"2017","venue":"IEEE Transactions on Cybernetics","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhai Yi-Ming et al., 2023] Ren Chuan-Xian Zhai Yi-Ming, Luo You-Wei, and Dai Dao-Qing. Maximizing conditional independence for unsupervised domain adaptation. SCI- ENCE CHINA Information Sciences, 2023.","title":"Maximizing conditional independence for unsupervised domain adaptation","authors":"Zhai Yi-Ming","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zhong et al., 2021] Li Zhong, Zhen Fang, Feng Liu, Bo Yuan, Guangquan Zhang, and Jie Lu. Bridging the the- oretical bound and deep algorithms for open set domain adaptation. IEEE Transactions on Neural Networks and Learning Systems, 2021.","title":"Bridging the theoretical bound and deep algorithms for open set domain adaptation","authors":"Li Zhong, Zhen Fang, Feng Liu, Bo Yuan, Guangquan Zhang, Jie Lu","year":"2021","venue":"IEEE Transactions on Neural Networks and Learning Systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}