{"type":"ScholarlyArticle","title":"Adversarial Bi-Regressor Network for Domain Adaptive Regression","authors":[{"name":"Haifeng Xia","slug":"haifeng-xia","given":"Haifeng","family":"Xia","affiliation":"Department of Computer Science , Tulane University , New Orleans , LA"},{"name":"Pu Wang","slug":"pu-wang","given":"Pu","family":"Wang","affiliation":"Mitsubishi Electric Research Laboratories (MERL) , Cambridge , MA"},{"name":"Toshiaki Koike-Akino","slug":"toshiaki-koike-akino","given":"Toshiaki","family":"Koike-Akino","affiliation":"Mitsubishi Electric Research Laboratories (MERL) , Cambridge , MA"},{"name":"Ye Wang","slug":"ye-wang","given":"Ye","family":"Wang","affiliation":"Mitsubishi Electric Research Laboratories (MERL) , Cambridge , MA"},{"name":"Philip Orlik","slug":"philip-orlik","given":"Philip","family":"Orlik","affiliation":"Mitsubishi Electric Research Laboratories (MERL) , Cambridge , MA"},{"name":"Zhengming Ding","slug":"zhengming-ding","given":"Zhengming","family":"Ding","affiliation":"Department of Computer Science , Tulane University , New Orleans , LA"}],"abstract":"Domain adaptation (DA) aims to transfer the knowledge of a well-labeled source domain to facilitate unlabeled target learning. When turning to specific tasks such as indoor (Wi-Fi) localization, it is essential to learn a cross-domain regressor to mitigate the domain shift. This paper proposes a novel method Adversarial Bi-Regressor Network (ABRNet) to seek more effective cross- domain regression model. Specifically, a discrepant bi-regressor architecture is developed to maximize the difference of bi-regressor to discover uncertain target instances far from the source distribution, and then an adversarial training mechanism is adopted between feature extractor and dual regressors to produce domain-invariant representations. To further bridge the large domain gap, a domain- specific augmentation module is designed to synthesize two source-similar and target-similar inter- mediate domains to gradually eliminate the original domain mismatch. The empirical studies on two cross-domain regressive benchmarks illustrate the power of our method on solving the domain adaptive regression (DAR) problem.","doi":"10.24963/ijcai.2022/501","url":"https://ijcai.org/proceedings/2022/501","pdf":"https://ijcai.org/proceedings/2022/0501.pdf","markdown":"https://ijcai.org/proceedings/2022/501.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/501","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":501,"pages":{"first":3608,"last":3614},"keywords":["Machine Learning: Unsupervised Learning","Machine Learning: Regression","Machine Learning: Representation learning","Robotics: Localization, Mapping, State Estimatino"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986779","length_sec":85,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984922","length_sec":210,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Arnold and Schaich, 2021] Maximilian Arnold and Frank Schaich. Indoor positioning systems: Smart fusion of a variety of sensor readings. ArXiv preprint, 2021.","title":"Indoor positioning systems: Smart fusion of a variety of sensor readings","authors":"Arnold, Schaich, Maximilian Arnold, Frank Schaich","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Awais et al., 2021] Muhammad Awais, Fengwei Zhou, Hang Xu, Lanqing Hong, Ping Luo, and Sung-Ho Bae. Adversarial robustness for unsupervised domain adapta- tion. In ICCV, 2021.","title":"Adversarial robustness for unsupervised domain adaptation","authors":"Muhammad Awais, Fengwei Zhou, Hang Xu, Lanqing Hong, Ping Luo, Sung-Ho Bae","year":"2021","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chang et al., 2019] Woong-Gi Chang, Tackgeun You, Seonguk Seo, Suha Kwak, and Bohyung Han. Domain- specific batch normalization for unsupervised domain adaptation. In CVPR, 2019.","title":"Domainspecific batch normalization for unsupervised domain adaptation","authors":"Chang","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2021] Xinyang Chen, Sinan Wang, Jianmin Wang, and Mingsheng Long. Representation subspace dis- tance for domain adaptation regression. In ICML, 2021.","title":"Representation subspace distance for domain adaptation regression","authors":"Xinyang Chen, Sinan Wang, Jianmin Wang, Mingsheng Long","year":"2021","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Courty et al., 2017] Nicolas Courty, Rémi Flamary, Amaury Habrard, and Alain Rakotomamonjy. Joint distribution optimal transportation for domain adaptation. ArXiv preprint, 2017.","title":"Joint distribution optimal transportation for domain adaptation","authors":"Nicolas Courty, Rémi Flamary, Amaury Habrard, Alain Rakotomamonjy","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Ganin and Lempitsky, 2015] Yaroslav Ganin and Victor Lempitsky. Unsupervised domain adaptation by backprop- agation. In ICML, 2015.","title":"Unsupervised domain adaptation by backpropagation","authors":"Yaroslav Ganin, Victor Lempitsky","year":"2015","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Gupta et al., 2014] Saurabh Gupta, Ross Girshick, and Pablo Arbeláez. Learning rich features from rgb-d images for object detection and segmentation. In ECCV, 2014.","title":"Learning rich features from rgb-d images for object detection and segmentation","authors":"Saurabh Gupta, Ross Girshick, Pablo Arbeláez","year":"2014","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[He and Chan, 2016] S. He and S.G. Chan. Wi-Fi fingerprint-based indoor positioning: Recent advances and comparisons. IEEE Communications Surveys & Tutorials, 2016.","title":"Wi-Fi fingerprint-based indoor positioning: Recent advances and comparisons","authors":"S He, S G Chan","year":"2016","venue":"IEEE Communications Surveys & Tutorials","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Higgins et al., 2017] Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, and Shakir Mohamed. beta-vae: Learning basic visual concepts with a constrained variational framework. In ICLR, 2017.","title":"beta-vae: Learning basic visual concepts with a constrained variational framework","authors":"Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed","year":"2017","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Jing et al., 2021] Taotao Jing, Bingrong Xu, and Zheng- ming Ding. Towards fair knowledge transfer for imbal- anced domain adaptation. IEEE Transactions on Image Processing, 30:8200-8211, 2021.","title":"Towards fair knowledge transfer for imbalanced domain adaptation","authors":"Taotao Jing, Bingrong Xu, Zhengming Ding","year":"2021","venue":"IEEE Transactions on Image Processing","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Koike-Akino et al., 2020] T. Koike-Akino, P. Wang, M. Pa- jovic, H. Sun, and P. V. Orlik. Fingerprinting-based in- door localization with commercial mmwave WiFi: A deep learning approach. IEEE Access, 2020.","title":"Fingerprinting-based indoor localization with commercial mmwave WiFi: A deep learning approach","authors":"T Koike-Akino, P Wang, M Pajovic, H Sun, P V Orlik","year":"2020","venue":"IEEE Access","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Krizhevsky et al., 2012] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. NIPS, 2012.","title":"Imagenet classification with deep convolutional neural networks","authors":"Alex Krizhevsky, Ilya Sutskever, Geoffrey E Hinton","year":"2012","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[LeCun et al., 1998] Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learning ap- plied to document recognition. IEEE, 1998.","title":"Gradient-based learning applied to document recognition","authors":"Yann Lecun, Léon Bottou, Yoshua Bengio, Patrick Haffner","year":"1998","venue":"IEEE","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Li et al., 2020] Mengxue Li, Yi-Ming Zhai, You-Wei Luo, and Peng-Fei Ge. Enhanced transport distance for unsu- pervised domain adaptation. In CVPR, 2020.","title":"Enhanced transport distance for unsupervised domain adaptation","authors":"Li","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Long et al., 2015] Mingsheng Long, Yue Cao, Jianmin Wang, and Michael Jordan. Learning transferable features with deep adaptation networks. In ICML, 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":16,"raw":"[Na et al., 2021] Jaemin Na, Heechul Jung, and Hyung Jin Chang. Fixbi: Bridging domain spaces for unsupervised domain adaptation. In CVPR, 2021.","title":"Fixbi: Bridging domain spaces for unsupervised domain adaptation","authors":"Jaemin Na, Heechul Jung, Jin Hyung, Chang","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Pan et al., 2010] Sinno Jialin Pan, Ivor W Tsang, James T Kwok, and Qiang Yang. Domain adaptation via transfer component analysis. IEEE transactions on neural net- works, 2010.","title":"Domain adaptation via transfer component analysis","authors":"Ivor W Sinno Jialin Pan, James T Tsang, Qiang Kwok, Yang","year":"2010","venue":"IEEE transactions on neural networks","doi":null,"url":null,"internal_url":"/proceedings/2009/200"},{"position":18,"raw":"[Pan et al., 2019] Yingwei Pan, Ting Yao, Yehao Li, Yu Wang, Chong-Wah Ngo, and Tao Mei. Transferrable prototypical networks for unsupervised domain adapta- tion. In CVPR, 2019.","title":"Transferrable prototypical networks for unsupervised domain adaptation","authors":"Pan","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Saito et al., 2018] Kuniaki Saito, Kohei Watanabe, and Yoshitaka Ushiku. Maximum classifier discrepancy for unsupervised domain adaptation. In CVPR, 2018.","title":"Maximum classifier discrepancy for unsupervised domain adaptation","authors":"Kuniaki Saito, Kohei Watanabe, Yoshitaka Ushiku","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Sellami and Tabbone, 2022] Akrem Sellami and Salvatore Tabbone. Deep neural networks-based relevant latent rep- resentation learning for hyperspectral image classification. Pattern Recognition, 2022.","title":"Akrem Sellami and Salvatore Tabbone. Deep neural networks-based relevant latent representation learning for hyperspectral image classification","authors":"Tabbone Sellami","year":"2022","venue":"Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Tong et al., 2021] Xinyu Tong, Hao Li, and Xiaohua Tian. Wi-fi localization enabling self-calibration. IEEE/ACM Transactions on Networking, 2021.","title":"Wi-fi localization enabling self-calibration","authors":"Xinyu Tong, Hao Li, Xiaohua Tian","year":"2021","venue":"IEEE/ACM Transactions on Networking","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wang et al., 2017] X. Wang, L. Gao, S. Mao, and S. Pandey. CSI-based fingerprinting for indoor localization: A deep learning approach. IEEE Trans. on Vehicular Technology, 2017.","title":"CSI-based fingerprinting for indoor localization: A deep learning approach","authors":"Wang","year":"2017","venue":"IEEE Trans. on Vehicular Technology","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Xia and Ding, 2020] Haifeng Xia and Zhengming Ding. Structure preserving generative cross-domain learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4364-4373, 2020.","title":"Structure preserving generative cross-domain learning","authors":"Ding ; ] Haifeng Xia, Zhengming Xia, Ding","year":"2020","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Xia et al., 2021a] Haifeng Xia, Taotao Jing, Chen Chen, and Zhengming Ding. Semi-supervised domain adaptive retrieval via discriminative hashing learning. In Proceed- ings of the 29th ACM International Conference on Multi- media, pages 3853-3861, 2021.","title":"Semi-supervised domain adaptive retrieval via discriminative hashing learning","authors":"Xia","year":"2021","venue":"Proceedings of the 29th ACM International Conference on Multimedia","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Xia et al., 2021b] Haifeng Xia, Handong Zhao, and Zheng- ming Ding. Adaptive adversarial network for source-free domain adaptation. In Proceedings of the IEEE/CVF In- ternational Conference on Computer Vision, pages 9010- 9019, 2021.","title":"Adaptive adversarial network for source-free domain adaptation","authors":"Xia","year":"2021","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Xu et al., 2014] Yong Xu, Jun Du, Li-Rong Dai, and Chin- Hui Lee. A regression approach to speech enhancement based on deep neural networks. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014.","title":"A regression approach to speech enhancement based on deep neural networks","authors":"Yong Xu, Jun Du, Li-Rong Dai, Chin-Hui Lee","year":"2014","venue":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","doi":null,"url":null,"internal_url":null},{"position":27,"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 ICCV, 2019.","title":"Larger norm more transferable: An adaptive feature norm approach for unsupervised domain adaptation","authors":"Xu","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Yamada et al., 2014] Makoto Yamada, Leonid Sigal, and Yi Chang. Domain adaptation for structured regression. International Journal of Computer Vision, 2014.","title":"Domain adaptation for structured regression","authors":"Makoto Yamada, Leonid Sigal, Yi Chang","year":"2014","venue":"International Journal of Computer Vision","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhou et al., 2021] Mu Zhou, Yaohua Li, Muhammad Junaid Tahir, Xiaolong Geng, Yong Wang, and Wei He. Integrated statistical test of signal distributions and access point con- tributions for wi-fi indoor localization. IEEE Transactions on Vehicular Technology, 2021.","title":"Integrated statistical test of signal distributions and access point contributions for wi-fi indoor localization","authors":"Mu Zhou, Yaohua Li, Muhammad Junaid Tahir, Xiaolong Geng, Yong Wang, Wei He","year":"2021","venue":"IEEE Transactions on Vehicular Technology","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}