{"type":"ScholarlyArticle","title":"Self-paced Supervision for Multi-source Domain Adaptation","authors":[{"name":"Zengmao Wang","slug":"zengmao-wang","given":"Zengmao","family":"Wang","affiliation":"National Engineering Research Center for Multimedia Software , School of Computer Science , Institute of Artificial Intelligence , Science and Hubei Key Laboratory of Multimedia and Network Communication Engineering , Wuhan University , China"},{"name":"Chaoyang Zhou","slug":"chaoyang-zhou","given":"Chaoyang","family":"Zhou","affiliation":"National Engineering Research Center for Multimedia Software , School of Computer Science , Institute of Artificial Intelligence , Science and Hubei Key Laboratory of Multimedia and Network Communication Engineering , Wuhan University , China"},{"name":"Bo Du","slug":"bo-du","given":"Bo","family":"Du","affiliation":"National Engineering Research Center for Multimedia Software , School of Computer Science , Institute of Artificial Intelligence , Science and Hubei Key Laboratory of Multimedia and Network Communication Engineering , Wuhan University , China"},{"name":"Fengxiang He","slug":"fengxiang-he","given":"Fengxiang","family":"He","affiliation":"JD Explore Academy , JD.com Inc , China"}],"abstract":"Multi-source domain adaptation has attracted great attention in machine learning community. Most of these methods focus on weighting the predictions produced by the adaptation networks of different domains. Thus the domain shifts between certain of domains and target domain are not effectively relieved, resulting in that these domains are not fully exploited and even may have a negative influence on multi-source domain adaptation task. To address such challenge, we propose a multi-source domain adaptation method to gradually improve the adaptation ability of each source domain by producing more high-confident pseudo-labels with self-paced learning for conditional distribution alignment. The proposed method first trains several separate domain branch networks with single domains and an ensemble branch network with all domains. Then we obtain some high-confident pseudo-labels with the branch networks and learn the branch specific pseudo-labels with self-paced learning. Each branch network reduces the domain gap by aligning the conditional distribution with its branch specific pseudo-labels and the pseudo-labels provided by all branch networks. Experiments on Office31, Office-Home and DomainNet show that the proposed method outperforms the state-of-the-art methods.","doi":"10.24963/ijcai.2022/493","url":"https://ijcai.org/proceedings/2022/493","pdf":"https://ijcai.org/proceedings/2022/0493.pdf","markdown":"https://ijcai.org/proceedings/2022/493.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/493","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":"Machine Learning","track":"Main Track","number":493,"pages":{"first":3551,"last":3557},"keywords":["Computer Vision: Transfer, low-shot, semi- and un- supervised learning","Machine Learning: Multi-task and Transfer Learning","Computer Vision: Machine Learning for Vision"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986833","length_sec":83,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984976","length_sec":346,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Fu et al., 2021] Yangye Fu, Ming Zhang, Xing Xu, Zuo Cao, Chao Ma, Yanli Ji, Kai Zuo, and Huimin Lu. Partial feature selection and alignment for multi-source domain adaptation. In IEEE CVPR, pages 16654-16663, 2021.","title":"Partial feature selection and alignment for multi-source domain adaptation","authors":"Fu","year":"2021","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ganin and Lempitsky, 2015] Yaroslav Ganin and Victor Lempitsky. Unsupervised domain adaptation by backprop- agation. In ICML, pages 1180-1189, 2015.","title":"Unsupervised domain adaptation by backpropagation","authors":"Yaroslav Ganin, Victor Lempitsky","year":"2015","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Guo et al., 2020] Han Guo, Ramakanth Pasunuru, and Mo- hit Bansal. Multi-source domain adaptation for text clas- sification via distancenet-bandits. In AAAI, pages 7830- 7838, 2020.","title":"Multi-source domain adaptation for text classification via distancenet-bandits","authors":"Han Guo, Ramakanth Pasunuru, Mohit Bansal","year":"2020","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[He et al., 2021] Jianzhong He, Xu Jia, Shuaijun Chen, and Jianzhuang Liu. Multi-source domain adaptation with col- laborative learning for semantic segmentation. In IEEE CVPR, pages 11008-11017, 2021.","title":"Multi-source domain adaptation with collaborative learning for semantic segmentation","authors":"Jianzhong He, Xu Jia, Shuaijun Chen, Jianzhuang Liu","year":"2021","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Jiang et al., 2020] Xiang Jiang, Qicheng Lao, Stan Matwin, and Mohammad Havaei. Implicit class-conditioned do- main alignment for unsupervised domain adaptation. In ICML, pages 4816-4827, 2020.","title":"Implicit class-conditioned domain alignment for unsupervised domain adaptation","authors":"Xiang Jiang, Qicheng Lao, Stan Matwin, Mohammad Havaei","year":"2020","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Li et al., 2021] Ruihuang Li, Xu Jia, Jianzhong He, Shuai- jun Chen, and Qinghua Hu. T-svdnet: Exploring high- order prototypical correlations for multi-source domain adaptation. In IEEE CVPR, pages 9991-10000, 2021.","title":"T-svdnet: Exploring highorder prototypical correlations for multi-source domain adaptation","authors":"Ruihuang Li, Xu Jia, Jianzhong He, Shuaijun Chen, Qinghua Hu","year":"2021","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Long et al., 2015] Mingsheng Long, Yue Cao, Jianmin Wang, and Michael Jordan. Learning transferable features with deep adaptation networks. In ICML, pages 97-105, 2015.","title":"Learning transferable features with deep adaptation networks","authors":"Mingsheng Long, Yue Cao, Jianmin Wang, Michael Jordan","year":"2015","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ouyang et al., 2020] Cheng Ouyang, Carlo Biffi, Chen Chen, Turkay Kart, Huaqi Qiu, and Daniel Rueckert. Self- supervision with superpixels: Training few-shot medical image segmentation without annotation. In ECCV, pages 762-780, 2020.","title":"Selfsupervision with superpixels: Training few-shot medical image segmentation without annotation","authors":"Cheng Ouyang, Carlo Biffi, Chen Chen, Turkay Kart, Huaqi Qiu, Daniel Rueckert","year":"2020","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Peng et al., 2019] X. Peng, Q. Bai, X. Xia, Z. Huang, and B. Wang. Moment matching for multi-source domain adaptation. In IEEE CVPR, 2019.","title":"Moment matching for multi-source domain adaptation","authors":"Peng","year":"2019","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Saito et al., 2018] Kuniaki Saito, Kohei Watanabe, Yoshi- taka Ushiku, and Tatsuya Harada. Maximum classifier discrepancy for unsupervised domain adaptation. In IEEE CVPR, pages 3723-3732, 2018.","title":"Maximum classifier discrepancy for unsupervised domain adaptation","authors":"Kuniaki Saito, Kohei Watanabe, Yoshitaka Ushiku, Tatsuya Harada","year":"2018","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Sun and Saenko, 2016] Baochen Sun and Kate Saenko. Deep coral: Correlation alignment for deep domain adap- tation. In ECCV, pages 443-450, 2016.","title":"Deep coral: Correlation alignment for deep domain adaptation","authors":"Saenko ; Sun, Baochen Sun, Kate Saenko","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Venkat and Kundu, 2020] Naveen Venkat and Jogen- dra Nath Kundu. Your classifier can secretly suffice multi-source domain adaptation. In NeurIPS, 2020.","title":"Your classifier can secretly suffice multi-source domain adaptation","authors":"Naveen Venkat, Jogendra Nath, Kundu","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Wang et al., 2017] Zengmao Wang, Bo Du, Lefei Zhang, Ruimin Hu, and Dacheng Tao. On gleaning knowledge from multiple domains for active learning. In IJCAI, pages 3013-3019, 2017.","title":"On gleaning knowledge from multiple domains for active learning","authors":"Wang","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/420"},{"position":14,"raw":"[Wang et al., 2020] Hang Wang, Minghao Xu, Bingbing Ni, and Wenjun Zhang. Learning to combine: Knowledge ag- gregation for multi-source domain adaptation. In ECCV, pages 727-744, 2020.","title":"Learning to combine: Knowledge aggregation for multi-source domain adaptation","authors":"Hang Wang, Minghao Xu, Bingbing Ni, Wenjun Zhang","year":"2020","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Wen et al., 2020] Junfeng Wen, Russell Greiner, and Dale Schuurmans. Domain aggregation networks for multi- source domain adaptation. In ICML, pages 10214-10224, 2020.","title":"Domain aggregation networks for multisource domain adaptation","authors":"Junfeng Wen, Russell Greiner, Dale Schuurmans","year":"2020","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Yan et al., 2017] Hongliang Yan, Yukang Ding, Peihua Li, Qilong Wang, Yong Xu, and Wangmeng Zuo. Mind the class weight bias: Weighted maximum mean discrepancy for unsupervised domain adaptation. In IEEE CVPR, pages 2272-2281, 2017.","title":"Mind the class weight bias: Weighted maximum mean discrepancy for unsupervised domain adaptation","authors":"Hongliang Yan, Yukang Ding, Peihua Li, Qilong Wang, Yong Xu, Wangmeng Zuo","year":"2017","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Zhang et al., 2019] Yuchen Zhang, Tianle Liu, Mingsheng Long, and Michael Jordan. Bridging theory and algorithm for domain adaptation. In ICML, pages 7404-7413, 2019.","title":"Bridging theory and algorithm for domain adaptation","authors":"Yuchen Zhang, Tianle Liu, Mingsheng Long, Michael Jordan","year":"2019","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Zhang et al., 2021] Dingwen Zhang, Junwei Han, Gong Cheng, and Ming-Hsuan Yang. Weakly supervised object localization and detection: A survey. IEEE TPAMI, 2021.","title":"Weakly supervised object localization and detection: A survey","authors":"Zhang","year":"2021","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Zhao et al., 2018] Han Zhao, Shanghang Zhang, Guanhang Wu, José MF Moura, Joao P Costeira, and Geoffrey J Gordon. Adversarial multiple source domain adaptation. NeurIPS, 31:8559-8570, 2018.","title":"Adversarial multiple source domain adaptation","authors":"Han Zhao, Shanghang Zhang, Guanhang Wu, M F José, Joao P Moura, Geoffrey J Costeira, Gordon","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Zhao et al., 2020] Sicheng Zhao, Guangzhi Wang, Shang- hang Zhang, Yang Gu, Yaxian Li, Zhichao Song, Pengfei Xu, Runbo Hu, Hua Chai, and Kurt Keutzer. Multi-source distilling domain adaptation. In AAAI, pages 12975- 12983, 2020.","title":"Multi-source distilling domain adaptation","authors":"Sicheng Zhao, Guangzhi Wang, Shanghang Zhang, Yang Gu, Yaxian Li, Zhichao Song, Pengfei Xu, Runbo Hu, Hua Chai, Kurt Keutzer","year":"2020","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Zhao et al., 2021] Sicheng Zhao, Bo Li, Pengfei Xu, Xi- angyu Yue, Guiguang Ding, and Kurt Keutzer. Madan: multi-source adversarial domain aggregation network for domain adaptation. IJCV, 129:2399-2424, 2021.","title":"Madan: multi-source adversarial domain aggregation network for domain adaptation","authors":"Sicheng Zhao, Bo Li, Pengfei Xu, Xiangyu Yue, Guiguang Ding, Kurt Keutzer","year":"2021","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Zheng and Yang, 2021] Zhedong Zheng and Yi Yang. Rec- tifying pseudo label learning via uncertainty estima- tion for domain adaptive semantic segmentation. IJCV, 129(4):1106-1120, 2021.","title":"Rectifying pseudo label learning via uncertainty estimation for domain adaptive semantic segmentation","authors":"Yang ; ] Zhedong Zheng, Yi Zheng, Yang","year":"2021","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Zhong et al., 2021] Li Zhong, Zhen Fang, Feng Liu, Jie Lu, Bo Yuan, and Guangquan Zhang. How does the combined risk affect the performance of unsupervised domain adap- tation approaches? In AAAI, pages 11079-11087, 2021.","title":"How does the combined risk affect the performance of unsupervised domain adaptation approaches?","authors":"Li Zhong, Zhen Fang, Feng Liu, Jie Lu, Bo Yuan, Guangquan Zhang","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zhu et al., 2019] Yongchun Zhu, Fuzhen Zhuang, and De- qing Wang. Aligning domain-specific distribution and classifier for cross-domain classification from multiple sources. In AAAI, pages 5989-5996, 2019.","title":"Aligning domain-specific distribution and classifier for cross-domain classification from multiple sources","authors":"Yongchun Zhu, Fuzhen Zhuang, Deqing Wang","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}