{"type":"ScholarlyArticle","title":"Multi-level Consistency Learning for Semi-supervised Domain Adaptation","authors":[{"name":"Zizheng Yan","slug":"zizheng-yan","given":"Zizheng","family":"Yan","affiliation":"Shenzhen Research Institute of Big Data , The Chinese University of Hong Kong , Shenzhen"},{"name":"Yushuang Wu","slug":"yushuang-wu","given":"Yushuang","family":"Wu","affiliation":"Shenzhen Research Institute of Big Data , The Chinese University of Hong Kong , Shenzhen"},{"name":"Guanbin Li","slug":"guanbin-li","given":"Guanbin","family":"Li","affiliation":"Sun Yat-sen University; Shenzhen Research Institute of Big Data , The Chinese University of Hong Kong , Shenzhen"},{"name":"Yipeng Qin","slug":"yipeng-qin","given":"Yipeng","family":"Qin","affiliation":"Cardiff University"},{"name":"Xiaoguang Han","slug":"xiaoguang-han","given":"Xiaoguang","family":"Han","affiliation":"Shenzhen Research Institute of Big Data , The Chinese University of Hong Kong , Shenzhen"},{"name":"Shuguang Cui","slug":"shuguang-cui","given":"Shuguang","family":"Cui","affiliation":"Shenzhen Research Institute of Big Data , The Chinese University of Hong Kong , Shenzhen"}],"abstract":"Semi-supervised domain adaptation (SSDA) aims to apply knowledge learned from a fully labeled source domain to a scarcely labeled target domain. In this paper, we propose a Multi-level Consistency Learning (MCL) framework for SSDA. Specifically, our MCL regularizes the consistency of different views of target domain samples at three levels: (i) at inter-domain level, we robustly and accurately align the source and target domains using a prototype-based optimal transport method that utilizes the pros and cons of different views of target samples; (ii) at intra-domain level, we facilitate the learning of both discriminative and compact target feature representations by proposing a novel class-wise contrastive clustering loss; (iii) at sample level, we follow standard practice and improve the prediction accuracy by conducting a consistency-based self-training. Empirically, we verified the effectiveness of our MCL framework on three popular SSDA benchmarks, i.e., VisDA2017, DomainNet, and Office-Home datasets, and the experimental results demonstrate that our MCL framework achieves the state-of-the-art performance.","doi":"10.24963/ijcai.2022/213","url":"https://ijcai.org/proceedings/2022/213","pdf":"https://ijcai.org/proceedings/2022/0213.pdf","markdown":"https://ijcai.org/proceedings/2022/213.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/213","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Computer Vision","track":"Main Track","number":213,"pages":{"first":1530,"last":1536},"keywords":["Computer Vision: Transfer, low-shot, semi- and un- supervised learning","Machine Learning: Semi-Supervised Learning"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986663","length_sec":79,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984806","length_sec":357,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Chen et al., 2020] Ting Chen, Simon Kornblith, Moham- mad Norouzi, and Geoffrey Hinton. A simple framework for contrastive learning of visual representations. In ICML, 2020.","title":"A simple framework for contrastive learning of visual representations","authors":"Ting Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey Hinton","year":"2020","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Courty et al., 2016] Nicolas Courty, Rémi Flamary, Devis Tuia, and Alain Rakotomamonjy. Optimal transport for domain adaptation. TPAMI, 2016.","title":"Optimal transport for domain adaptation","authors":"Nicolas Courty, Rémi Flamary, Devis Tuia, Alain Rakotomamonjy","year":"2016","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cubuk et al., 2020] Ekin D Cubuk, Barret Zoph, Jonathon Shlens, and Quoc V Le. Randaugment: Practical auto- mated data augmentation with a reduced search space. In CVPR Workshops, 2020.","title":"Randaugment: Practical automated data augmentation with a reduced search space","authors":"Barret Ekin D Cubuk, Jonathon Zoph, Quoc V Shlens, Le","year":"2020","venue":"CVPR Workshops","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Deng et al., 2009] Jia Deng, Wei Dong, Richard Socher, Li- Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In CVPR, 2009.","title":"Imagenet: A large-scale hierarchical image database","authors":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei","year":"2009","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Fatras et al., 2021] Kilian Fatras, Thibault Séjourné, Rémi Flamary, and Nicolas Courty. Unbalanced minibatch opti- mal transport; applications to domain adaptation. In ICML, 2021.","title":"Unbalanced minibatch optimal transport; applications to domain adaptation","authors":"Kilian Fatras, Thibault Séjourné, Rémi Flamary, Nicolas Courty","year":"2021","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[French et al., 2018] Geoffrey French, Michal Mackiewicz, and Mark Fisher. Self-ensembling for visual domain adap- tation. In ICLR, 2018.","title":"Self-ensembling for visual domain adaptation","authors":"Geoffrey French, Michal Mackiewicz, Mark Fisher","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ganin et al., 2016] Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, Franc ¸ois Laviolette, Mario Marchand, and Victor Lempitsky. Domain-adversarial training of neural networks. JMLR, 2016.","title":"Domain-adversarial training of neural networks","authors":"Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, Mario Franc ¸ois Laviolette, Victor Marchand, Lempitsky","year":"2016","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Grandvalet et al., 2005] Yves Grandvalet, Yoshua Bengio, et al. Semi-supervised learning by entropy minimization. In CAP, 2005.","title":"Semi-supervised learning by entropy minimization","authors":"Yves Grandvalet, Yoshua Bengio","year":"2005","venue":"CAP","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Jiang et al., 2020] Pin Jiang, Aming Wu, Yahong Han, Yun- feng Shao, Meiyu Qi, and Bingshuai Li. Bidirectional ad- versarial training for semi-supervised domain adaptation. In IJCAI, 2020.","title":"Bidirectional adversarial training for semi-supervised domain adaptation","authors":"Jiang","year":"2020","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2020/130"},{"position":10,"raw":"[Khosla et al., 2020] Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. Supervised con- trastive learning. In NeurIPS, 2020.","title":"Supervised contrastive learning","authors":"Khosla","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kim and Kim, 2020] Taekyung Kim and Changick Kim. Attract, perturb, and explore: Learning a feature alignment network for semi-supervised domain adaptation. In ECCV, 2020.","title":"Attract, perturb, and explore: Learning a feature alignment network for semi-supervised domain adaptation","authors":"Kim ; Kim, Taekyung Kim, Changick Kim","year":"2020","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li and Hospedales, 2020] Da Li and Timothy Hospedales. Online meta-learning for multi-source and semi- supervised domain adaptation. In ECCV, 2020.","title":"Da Li and Timothy Hospedales. Online meta-learning for multi-source and semisupervised domain adaptation","authors":"Hospedales Li","year":"2020","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li et al., 2021a] Jichang Li, Guanbin Li, Yemin Shi, and Yizhou Yu. Cross-domain adaptive clustering for semi- supervised domain adaptation. In CVPR, 2021.","title":"Cross-domain adaptive clustering for semisupervised domain adaptation","authors":"Li","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Li et al., 2021b] Kai Li, Chang Liu, Handong Zhao, Yulun Zhang, and Yun Fu. Ecacl: A holistic framework for semi- supervised domain adaptation. In ICCV, 2021.","title":"Ecacl: A holistic framework for semisupervised domain adaptation","authors":"Li","year":"2021","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Liang et al., 2021] Jian Liang, Dapeng Hu, and Jiashi Feng. Domain adaptation with auxiliary target domain-oriented classifier. In CVPR, 2021.","title":"Domain adaptation with auxiliary target domain-oriented classifier","authors":"Jian Liang, Dapeng Hu, Jiashi Feng","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":16,"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 ICCV, 2013.","title":"Transfer feature learning with joint distribution adaptation","authors":"Mingsheng Long, Jianmin Wang, Guiguang Ding, Jiaguang Sun, Philip S Yu","year":"2013","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":17,"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":18,"raw":"[Peng et al., 2019] Xingchao Peng, Qinxun Bai, Xide Xia, Zijun Huang, Kate Saenko, and Bo Wang. Moment match- ing for multi-source domain adaptation. In ICCV, 2019.","title":"Moment matching for multi-source domain adaptation","authors":"Peng","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Qin et al., 2021] Can Qin, Lichen Wang, Qianqian Ma, Yu Yin, Huan Wang, and Yun Fu. Contradictory struc- ture learning for semi-supervised domain adaptation. In SDM, 2021.","title":"Contradictory structure learning for semi-supervised domain adaptation","authors":"Qin","year":"2021","venue":"SDM","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Saito et al., 2019] Kuniaki Saito, Donghyun Kim, Stan Sclaroff, Trevor Darrell, and Kate Saenko. Semi- supervised domain adaptation via minimax entropy. In ICCV, 2019.","title":"Semisupervised domain adaptation via minimax entropy","authors":"Kuniaki Saito, Donghyun Kim, Stan Sclaroff, Trevor Darrell, Kate Saenko","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Singh et al., 2021] Anurag Singh, Naren Doraiswamy, Sawa Takamuku, Megh Bhalerao, Titir Dutta, Soma Biswas, Aditya Chepuri, Balasubramanian Vengatesan, and Naotake Natori. Improving semi-supervised domain adaptation using effective target selection and semantics. In CVPRW, 2021.","title":"Improving semi-supervised domain adaptation using effective target selection and semantics","authors":"Anurag Singh, Naren Doraiswamy, Sawa Takamuku, Megh Bhalerao, Titir Dutta, Soma Biswas, Aditya Chepuri, Balasubramanian Vengatesan, Naotake Natori","year":"2021","venue":"CVPRW","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Singh, 2021] Ankit Singh. Clda: Contrastive learning for semi-supervised domain adaptation. In NeurlPS, 2021.","title":"Clda: Contrastive learning for semi-supervised domain adaptation","authors":"Ankit Singh","year":"2021","venue":"NeurlPS","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Sohn et al., 2020] Kihyuk Sohn, David Berthelot, Chun- Liang Li, Zizhao Zhang, Nicholas Carlini, Ekin D Cubuk, Alex Kurakin, Han Zhang, and Colin Raffel. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. In NeurIPS, 2020.","title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","authors":"Sohn","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Venkateswara et al., 2017] Hemanth Venkateswara, Jose Eusebio, Shayok Chakraborty, and Sethuraman Pan- chanathan. Deep hashing network for unsupervised do- main adaptation. In CVPR, 2017.","title":"Deep hashing network for unsupervised domain adaptation","authors":"Hemanth Venkateswara, Jose Eusebio, Shayok Chakraborty, Sethuraman Panchanathan","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Xie et al., 2019] Qizhe Xie, Zihang Dai, Eduard Hovy, Minh-Thang Luong, and Quoc V Le. Unsupervised data augmentation for consistency training. In NeurIPS, 2019.","title":"Unsupervised data augmentation for consistency training","authors":"Xie","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Yang et al., 2021] Luyu Yang, Yan Wang, Mingfei Gao, Abhinav Shrivastava, Kilian Q. Weinberger, Wei-Lun Chao, and Ser-Nam Lim. Deep co-training with task de- composition for semi-supervised domain adaptation. In ICCV, 2021.","title":"Deep co-training with task decomposition for semi-supervised domain adaptation","authors":"Yang","year":"2021","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Yao et al., 2022] Huifeng Yao, Xiaowei Hu, and Xi- aomeng Li. Enhancing pseudo label quality for semi- superviseddomain-generalized medical image segmenta- tion. arXiv preprint arXiv:2201.08657, 2022.","title":"Enhancing pseudo label quality for semisuperviseddomain-generalized medical image segmentation","authors":"Yao","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}