{"type":"ScholarlyArticle","title":"Multi-Level Metric Learning via Smoothed Wasserstein Distance","authors":[{"name":"Jie Xu","slug":"jie-xu","given":"Jie","family":"Xu","affiliation":"School of Electronic Engineering , Xidian University , Xi'an 710071 , China; Electrical and Computer Engineering , University of Pittsburgh , PA , 15261 , USA"},{"name":"Lei Luo","slug":"lei-luo","given":"Lei","family":"Luo","affiliation":"Electrical and Computer Engineering , University of Pittsburgh , PA , 15261 , USA"},{"name":"Cheng Deng","slug":"cheng-deng","given":"Cheng","family":"Deng","affiliation":"School of Electronic Engineering , Xidian University , Xi'an 710071 , China"},{"name":"Heng Huang","slug":"heng-huang","given":"Heng","family":"Huang","affiliation":"Electrical and Computer Engineering , University of Pittsburgh , PA , 15261 , USA; School of Electronic Engineering , Xidian University , Xi'an 710071 , China"}],"abstract":"Traditional metric learning methods aim to learn a single Mahalanobis distance metric M, which, however, is not discriminative enough to characterize the complex and heterogeneous data. Besides, if the descriptors of the data are not strictly aligned, Mahalanobis distance would fail to exploit the relations among them. To tackle these problems, in this paper, we propose a multi-level metric learning method using a smoothed Wasserstein distance to characterize the errors between any two samples, where the ground distance is considered as a Mahalanobis distance. Since smoothed Wasserstein distance provides not only a distance value but also a flow-network indicating how the probability mass is optimally transported between the bins, it is very effective in comparing two samples whether they are aligned or not. In addition, to make full use of the global and local structures that exist in data features, we further model the commonalities between various classification through a shared distance matrix and the classification-specific idiosyncrasies with additional auxiliary distance matrices. An efficient algorithm is developed to solve the proposed new model. Experimental evaluations on four standard databases show that our method obviously outperforms other state-of-the-art methods.","doi":"10.24963/ijcai.2018/405","url":"https://ijcai.org/proceedings/2018/405","pdf":"https://ijcai.org/proceedings/2018/0405.pdf","markdown":"https://ijcai.org/proceedings/2018/405.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/405","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Machine Learning","track":"Main track","number":405,"pages":{"first":2919,"last":2925},"keywords":["Machine Learning: Machine Learning","Computer Vision: Computer Vision"],"videos":[],"references":[{"position":1,"raw":"[Bisot et al., 2015] Victor Bisot, Slim Essid, and Gaël Richard. Hog and subband power distribution image fea- tures for acoustic scene classification. In EUSIPCO, pages 719-723. IEEE, 2015.","title":"Hog and subband power distribution image features for acoustic scene classification","authors":"Bisot","year":"2015","venue":"EUSIPCO","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chan and Vasconcelos, 2005] Antoni B Chan and Nuno Vasconcelos. Probabilistic kernels for the classification of auto-regressive visual processes. In CVPR, pages 846- 851, 2005.","title":"Probabilistic kernels for the classification of auto-regressive visual processes","authors":"B Antoni, Nuno Chan, Vasconcelos","year":"2005","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cuturi, 2013] Marco Cuturi. Sinkhorn distances: Light- speed computation of optimal transport. In NIPS, pages 2292-2300, 2013.","title":"Sinkhorn distances: Lightspeed computation of optimal transport","authors":"Marco Cuturi","year":"2013","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Davis et al., 2007] Jason V Davis, Brian Kulis, Prateek Jain, Suvrit Sra, and Inderjit S Dhillon. Information-theoretic metric learning. In ICML, pages 209-216. ACM, 2007.","title":"Information-theoretic metric learning","authors":"Jason V Davis, Brian Kulis, Prateek Jain, Suvrit Sra, Inderjit S Dhillon","year":"2007","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Fan et al., 2008] Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, and Chih-Jen Lin. Liblinear: A library for large linear classification. Journal of machine learning research, 9(Aug):1871-1874, 2008.","title":"Liblinear: A library for large linear classification","authors":"Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, Chih-Jen Lin","year":"2008","venue":"Journal of machine learning research","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Guillaumin et al., 2009] Matthieu Guillaumin, Jakob Ver- beek, and Cordelia Schmid. Is that you? metric learning approaches for face identification. In ICCV, pages 498- 505. IEEE, 2009.","title":"Is that you? metric learning approaches for face identification","authors":"Matthieu Guillaumin, Jakob Verbeek, Cordelia Schmid","year":"2009","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hirzer et al., 2011] Martin Hirzer, Csaba Beleznai, Peter M Roth, and Horst Bischof. Person re-identification by descriptive and discriminative classification. In Scan- dinavian conference on Image analysis, pages 91-102. Springer, 2011.","title":"Person re-identification by descriptive and discriminative classification","authors":"Martin Hirzer, Csaba Beleznai, Peter M Roth, Horst Bischof","year":"2011","venue":"Scandinavian conference on Image analysis","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hu et al., 2014] Junlin Hu, Jiwen Lu, and Yap-Peng Tan. Discriminative deep metric learning for face verification in the wild. In CVPR, pages 1875-1882, 2014.","title":"Discriminative deep metric learning for face verification in the wild","authors":"Hu","year":"2014","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Huo et al., 2016] Zhouyuan Huo, Feiping Nie, and Heng Huang. Robust and effective metric learning using capped trace norm: Metric learning via capped trace norm. In SIGKDD, pages 1605-1614. ACM, 2016.","title":"Robust and effective metric learning using capped trace norm: Metric learning via capped trace norm","authors":"Huo","year":"2016","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Koestinger et al., 2012] Martin Koestinger, Martin Hirzer, Paul Wohlhart, Peter M Roth, and Horst Bischof. Large scale metric learning from equivalence constraints. In CVPR, pages 2288-2295. IEEE, 2012.","title":"Large scale metric learning from equivalence constraints","authors":"Martin Koestinger, Martin Hirzer, Paul Wohlhart, Peter M Roth, Horst Bischof","year":"2012","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Law et al., 2014] Marc T Law, Nicolas Thome, and Matthieu Cord. Fantope regularization in metric learning. In CVPR, pages 1051-1058, 2014.","title":"Fantope regularization in metric learning","authors":"Nicolas Marc T Law, Matthieu Thome, Cord","year":"2014","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2017] WUCHEN Li, ERNEST K Ryu, STANLEY Osher, WOTAO Yin, and WILFRID Gangbo. A parallel method for earth mover's distance. UCLA Comput. Appl. Math. Pub.(CAM) Rep, pages 17-12, 2017.","title":"A parallel method for earth mover's distance","authors":"Li","year":"2017","venue":"UCLA Comput. Appl. Math. Pub.(CAM) Rep","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liao et al., 2015] Shengcai Liao, Yang Hu, Xiangyu Zhu, and Stan Z Li. Person re-identification by local maximal occurrence representation and metric learning. In CVPR, pages 2197-2206, 2015.","title":"Person re-identification by local maximal occurrence representation and metric learning","authors":"Shengcai Liao, Yang Hu, Xiangyu Zhu, Stan Z Li","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ling and Okada, 2007] Haibin Ling and Kazunori Okada. An efficient earth mover's distance algorithm for robust histogram comparison. IEEE transactions on pattern anal- ysis and machine intelligence, 29(5):840-853, 2007.","title":"An efficient earth mover's distance algorithm for robust histogram comparison","authors":"Haibin Ling, Kazunori Okada","year":"2007","venue":"IEEE transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Lu et al., 2014] Jiwen Lu, Xiuzhuang Zhou, Yap-Pen Tan, Yuanyuan Shang, and Jie Zhou. Neighborhood repulsed metric learning for kinship verification. IEEE transactions on pattern analysis and machine intelligence, 36(2):331- 345, 2014.","title":"Neighborhood repulsed metric learning for kinship verification","authors":"Jiwen Lu, Xiuzhuang Zhou, Yap-Pen Tan, Yuanyuan Shang, Jie Zhou","year":"2014","venue":"IEEE transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Luo and Huang, 2018] Lei Luo and Heng Huang. Matrix variate gaussian mixture distribution steered robust metric learning. In AAAI, pages 933--940, 2018.","title":"Matrix variate gaussian mixture distribution steered robust metric learning","authors":"Huang ; ] Lei Luo, Heng Luo, Huang","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Mignon and Jurie, 2012] Alexis Mignon and Frédéric Jurie. Pcca: A new approach for distance learning from sparse pairwise constraints. In CVPR, pages 2666-2672. IEEE, 2012.","title":"Pcca: A new approach for distance learning from sparse pairwise constraints","authors":"Alexis Mignon, Frédéric Jurie","year":"2012","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Pedagadi et al., 2013] Sateesh Pedagadi, James Orwell, Sergio Velastin, and Boghos Boghossian. Local fisher discriminant analysis for pedestrian re-identification. In CVPR, pages 3318-3325, 2013.","title":"Local fisher discriminant analysis for pedestrian re-identification","authors":"Sateesh Pedagadi, James Orwell, Sergio Velastin, Boghos Boghossian","year":"2013","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Peterson, 2009] Leif E Peterson. K-nearest neighbor. Schol- arpedia, 4(2):1883, 2009.","title":"K-nearest neighbor","authors":"Leif E Peterson","year":"2009","venue":"Scholarpedia","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Rolet et al., 2016] Antoine Rolet, Marco Cuturi, and Gabriel Peyré. Fast dictionary learning with a smoothed wasserstein loss. In Artificial Intelligence and Statistics, pages 630-638, 2016.","title":"Fast dictionary learning with a smoothed wasserstein loss","authors":"Rolet","year":"2016","venue":"Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Roth et al., 2014] Peter M Roth, Martin Hirzer, Martin Koestinger, Csaba Beleznai, and Horst Bischof. Maha- lanobis distance learning for person re-identification. In Person Re-Identification, pages 247-267. Springer, 2014. Rubner et al., 2000]","title":"Mahalanobis distance learning for person re-identification","authors":"Martin Peter M Roth, Martin Hirzer, Csaba Koestinger, Horst Beleznai, Bischof","year":"2000","venue":"Person Re-Identification","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"Yossi Rubner, Carlo Tomasi, and Leonidas J Guibas. The earth mover's distance as a metric for image retrieval. IJCV, 40(2):99-121, 2000.","title":"The earth mover's distance as a metric for image retrieval","authors":"Yossi Rubner, Carlo Tomasi, Leonidas J Guibas","year":"2000","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Sandler and Lindenbaum, 2011] Roman Sandler and Michael Lindenbaum. Nonnegative matrix factorization with earth mover's distance metric for image analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(8):1590-1602, 2011.","title":"Roman Sandler and Michael Lindenbaum. Nonnegative matrix factorization with earth mover's distance metric for image analysis","authors":"Lindenbaum Sandler","year":"2011","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wang et al., 2014] Hua Wang, Feiping Nie, and Heng Huang. Robust distance metric learning via simultaneous l1-norm minimization and maximization. In ICML, pages 1836-1844, 2014.","title":"Robust distance metric learning via simultaneous l1-norm minimization and maximization","authors":"Hua Wang, Feiping Nie, Heng Huang","year":"2014","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Weinberger and Saul, 2009] Kilian Q Weinberger and Lawrence K Saul. Distance metric learning for large mar- gin nearest neighbor classification. Journal of Machine Learning Research, 10(Feb):207-244, 2009.","title":"Distance metric learning for large margin nearest neighbor classification","authors":"Q Kilian, Lawrence K Weinberger, Saul","year":"2009","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Yan et al., 2007] Shuicheng Yan, Dong Xu, Benyu Zhang, Hong-Jiang Zhang, Qiang Yang, and Stephen Lin. Graph embedding and extensions: A general framework for di- mensionality reduction. IEEE transactions on pattern analysis and machine intelligence, 29(1):40-51, 2007.","title":"Graph embedding and extensions: A general framework for dimensionality reduction","authors":"Shuicheng Yan, Dong Xu, Benyu Zhang, Hong-Jiang Zhang, Qiang Yang, Stephen Lin","year":"2007","venue":"IEEE transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}