{"type":"ScholarlyArticle","title":"Adversarial Metric Learning","authors":[{"name":"Shuo Chen","slug":"shuo-chen","given":"Shuo","family":"Chen","affiliation":"School of Computer Science & Engineering , Nanjing University of Science & Technology"},{"name":"Chen Gong","slug":"chen-gong","given":"Chen","family":"Gong","affiliation":"School of Computer Science & Engineering , Nanjing University of Science & Technology; Key Laboratory of Intelligent Perception & Systems for High-Dimensional Information"},{"name":"Jian Yang","slug":"jian-yang","given":"Jian","family":"Yang","affiliation":"School of Computer Science & Engineering , Nanjing University of Science & Technology; Key Laboratory of Intelligent Perception & Systems for High-Dimensional Information; Jiangsu Key Laboratory of Image & Video Understanding for Social Security"},{"name":"Xiang Li","slug":"xiang-li","given":"Xiang","family":"Li","affiliation":"School of Computer Science & Engineering , Nanjing University of Science & Technology; Jiangsu Key Laboratory of Image & Video Understanding for Social Security"},{"name":"Yang Wei","slug":"yang-wei","given":"Yang","family":"Wei","affiliation":"School of Computer Science & Engineering , Nanjing University of Science & Technology; Jiangsu Key Laboratory of Image & Video Understanding for Social Security"},{"name":"Jun Li","slug":"jun-li","given":"Jun","family":"Li","affiliation":"Key Laboratory of Intelligent Perception & Systems for High-Dimensional Information; Jiangsu Key Laboratory of Image & Video Understanding for Social Security"}],"abstract":"In the past decades, intensive efforts have been put to design various loss functions and metric forms for metric learning problem. These improvements have shown promising results when the test data is similar to the training data. However, the trained models often fail to produce reliable distances on the ambiguous test pairs due to the different samplings between training set and test set. To address this problem, the Adversarial Metric Learning (AML) is proposed in this paper, which automatically generates adversarial pairs to remedy the sampling bias and facilitate robust metric learning. Specifically, AML consists of two adversarial stages, i.e. confusion and distinguishment. In confusion stage, the ambiguous but critical adversarial data pairs are adaptively generated to mislead the learned metric. In distinguishment stage, a metric is exhaustively learned to try its best to distinguish both adversarial pairs and original training pairs. Thanks to the challenges posed by the confusion stage in such competing process, the AML model is able to grasp plentiful difficult knowledge that has not been contained by the original training pairs, so the discriminability of AML can be significantly improved. The entire model is formulated into optimization framework, of which the global convergence is theoretically proved. The experimental results on toy data and practical datasets clearly demonstrate the superiority of AML to representative state-of-the-art metric learning models.","doi":"10.24963/ijcai.2018/279","url":"https://ijcai.org/proceedings/2018/279","pdf":"https://ijcai.org/proceedings/2018/0279.pdf","markdown":"https://ijcai.org/proceedings/2018/279.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/279","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":279,"pages":{"first":2021,"last":2027},"keywords":["Machine Learning: Dimensionality Reduction and Manifold Learning","Machine Learning: Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[Abdi and Williams, 2010] Hervé Abdi and Lynne J Williams. Principal component analysis. Wiley Interdisciplinary Reviews: Computational Statistics, 2(4):433-459, 2010.","title":"Principal component analysis","authors":"Williams ; Abdi, Hervé Abdi, Lynne J Williams","year":"2010","venue":"Wiley Interdisciplinary Reviews: Computational Statistics","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ahmed et al., 2015] Ejaz Ahmed, Michael Jones, and Tim K Marks. An improved deep learning architecture for person re- identification. In CVPR, pages 733-740, 2015.","title":"An improved deep learning architecture for person reidentification","authors":"Ejaz Ahmed, Michael Jones, Tim K Marks","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Asuncion and Newman, 2007] Arthur Asuncion and David New- man. Uci machine learning repository, 2007.","title":"Arthur Asuncion and David Newman","authors":"Asuncion, Newman","year":"2007","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bard, 2013] Jonathan F Bard. Practical Bilevel Optimization: Al- gorithms and Applications, volume 30. Springer Science & Busi- ness Media, 2013.","title":"Practical Bilevel Optimization: Algorithms and Applications","authors":"Jonathan F Bard","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bellman, 1997] Richard Bellman. Introduction to Matrix Analysis. SIAM, 1997.","title":"Introduction to Matrix Analysis","authors":"Richard Bellman","year":"1997","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Ben-Tal et al., 2009] Aharon Ben-Tal, Laurent El Ghaoui, and Arkadi Nemirovski. Robust Optimization. Princeton University Press, 2009.","title":"Robust Optimization","authors":"Aharon Ben-Tal, Laurent El Ghaoui, Arkadi Nemirovski","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Bishop, 2006] Christopher M Bishop. Pattern Recognition and Machine Learning. springer, 2006.","title":"Pattern Recognition and Machine Learning","authors":"M Christopher, Bishop","year":"2006","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Boyd and Vandenberghe, 2004] Stephen Boyd and Lieven Van- denberghe. Convex Optimization. Cambridge university, 2004.","title":"Stephen Boyd and Lieven Vandenberghe","authors":"Vandenberghe Boyd","year":"2004","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Brown et al., 2011] Matthew Brown, Gang Hua, and Simon Winder. Discriminative learning of local image descriptors. IEEE Transactions on Pattern Analysis and Machine Intelli- gence, 33(1):43-57, 2011.","title":"Discriminative learning of local image descriptors","authors":"Matthew Brown, Gang Hua, Simon Winder","year":"2011","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Cheung and Hamarneh, 2009] Warren Cheung and Ghassan Hamarneh. N-sift: n-dimensional scale invariant feature transform. IEEE Transactions on Image Processing, 18(9), 2009.","title":"N-sift: n-dimensional scale invariant feature transform","authors":"Hamarneh ; Cheung, Warren Cheung, Ghassan Hamarneh","year":"2009","venue":"IEEE Transactions on Image Processing","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Davis et al., 2007] Jason V Davis, Brian Kulis, Prateek Jain, Suvrit Sra, and Inderjit S Dhillon. Information-theoretic metric learn- ing. In ICML, pages 209-216, 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":12,"raw":"[Goodfellow et al., 2015] Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. Explaining and harnessing adversarial exam- ples. In ICLR, pages 212-227, 2015.","title":"Explaining and harnessing adversarial examples","authors":"Ian J Goodfellow, Jonathon Shlens, Christian Szegedy","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Harandi et al., 2017] Mehrtash Harandi, Mathieu Salzmann, and Richard Hartley. Joint dimensionality reduction and metric learn- ing: A geometric take. In ICML, pages 1943-1950, 2017.","title":"Joint dimensionality reduction and metric learning: A geometric take","authors":"Harandi","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Huang et al., 2007] Gary B Huang, Manu Ramesh, Tamara Berg, and Erik Learned-Miller. Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Technical report, Technical Report 07-49, University of Mas- sachusetts, Amherst, 2007.","title":"Labeled faces in the wild: A database for studying face recognition in unconstrained environments","authors":"Manu Gary B Huang, Tamara Ramesh, Erik Berg, Learned-Miller","year":"2007","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Huang et al., 2010] Kaizhu Huang, Rong Jin, Zenglin Xu, and Cheng-Lin Liu. Robust metric learning by smooth optimization. UAI, 2010.","title":"Robust metric learning by smooth optimization","authors":"Kaizhu Huang, Rong Jin, Zenglin Xu, Cheng-Lin Liu","year":"2010","venue":"UAI","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Li et al., 2017] Zheng Li, Yu Zhang, and Ying Wei. End-to-end adversarial memory network for cross-domain sentiment classifi- cation. In IJCAI, pages 2133-2140, 2017.","title":"End-to-end adversarial memory network for cross-domain sentiment classification","authors":"Zheng Li, Yu Zhang, Ying Wei","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/311"},{"position":17,"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":18,"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":"Lei Luo, Heng Huang","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Meyer et al., 2011] Gilles Meyer, Silvère Bonnabel, and Rodolphe Sepulchre. Regression on fixed-rank positive semidefinite matri- ces: a riemannian approach. Journal of Machine Learning Re- search, 12(Feb):593-625, 2011.","title":"Regression on fixed-rank positive semidefinite matrices: a riemannian approach","authors":"Gilles Meyer, Silvère Bonnabel, Rodolphe Sepulchre","year":"2011","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Nair and Hinton, 2010] Vinod Nair and Geoffrey E Hinton. Rec- tified linear units improve restricted boltzmann machines. In ICML, pages 807-814, 2010.","title":"Rectified linear units improve restricted boltzmann machines","authors":"Vinod Nair, Geoffrey E Hinton","year":"2010","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Noroozi et al., 2017] Vahid Noroozi, Lei Zheng, Sara Bahaadini, Sihong Xie, and Philip S Yu. Seven: Deep semi-supervised veri- fication networks. In IJCAI, pages 133-140, 2017.","title":"Seven: Deep semi-supervised verification networks","authors":"Vahid Noroozi, Lei Zheng, Sara Bahaadini, Sihong Xie, Philip S Yu","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/358"},{"position":22,"raw":"[Oh Song et al., 2016] Hyun Oh Song, Yu Xiang, Stefanie Jegelka, and Silvio Savarese. Deep metric learning via lifted structured feature embedding. In CVPR, pages 4004-4012, 2016.","title":"Deep metric learning via lifted structured feature embedding","authors":"Hyun Oh Song, Yu Xiang, Stefanie Jegelka, Silvio Savarese","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Perrot and Habrard, 2015] Michael Perrot and Amaury Habrard. Regressive virtual metric learning. In NIPS, 2015.","title":"Regressive virtual metric learning","authors":"Michael Perrot, Amaury Habrard","year":"2015","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Petersen et al., 2008] Kaare Brandt Petersen, Michael Syskind Pedersen, et al. The matrix cookbook. Technical University of Denmark, 7:15, 2008.","title":"The matrix cookbook","authors":"Petersen","year":"2008","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Simo-Serra et al., 2015] Edgar Simo-Serra, Eduard Trulls, Luis Ferraz, Iasonas Kokkinos, Pascal Fua, and Francesc Moreno- Noguer. Discriminative learning of deep convolutional feature point descriptors. In ICCV, pages 118-126, 2015.","title":"Discriminative learning of deep convolutional feature point descriptors","authors":"Simo-Serra","year":"2015","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Weinberger and Saul, 2009] Kilian Q Weinberger and Lawrence K Saul. Distance metric learning for large margin nearest neigh- bor 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":27,"raw":"[Xie and Xing, 2013] Pengtao Xie and Eric P Xing. Multi-modal distance metric learning. In IJCAI, pages 1806-1812, 2013.","title":"Multi-modal distance metric learning","authors":"Xing Xie, Pengtao Xie, Eric P Xing","year":"2013","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2013/267"},{"position":28,"raw":"[Yang et al., 2016] Xun Yang, Meng Wang, Luming Zhang, and Dacheng Tao. Empirical risk minimization for metric learning using privileged information. In IJCAI, pages 2266-2272, 2016.","title":"Empirical risk minimization for metric learning using privileged information","authors":"Xun Yang, Meng Wang, Luming Zhang, Dacheng Tao","year":"2016","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2016/323"},{"position":29,"raw":"[Ye et al., 2017] Han-Jia Ye, De-Chuan Zhan, Xue-Min Si, and Yuan Jiang. Learning mahalanobis distance metric: Considering instance disturbance helps. In IJCAI, pages 866-872, 2017.","title":"Learning mahalanobis distance metric: Considering instance disturbance helps","authors":"Han-Jia Ye, Xue-Min De-Chuan Zhan, Yuan Si, Jiang","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/463"},{"position":30,"raw":"[Zadeh et al., 2016] Pourya Zadeh, Reshad Hosseini, and Suvrit Sra. Geometric mean metric learning. In ICML, 2016.","title":"Geometric mean metric learning","authors":"Zadeh","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zagoruyko and Komodakis, 2015] Sergey Zagoruyko and Nikos Komodakis. Learning to compare image patches via convolu- tional neural networks. In ICCV, pages 4353-4361, 2015.","title":"Learning to compare image patches via convolutional neural networks","authors":"Komodakis Zagoruyko, Sergey Zagoruyko, Nikos Komodakis","year":"2015","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhan et al., 2009] De-Chuan Zhan, Ming Li, Yu-Feng Li, and Zhi- Hua Zhou. Learning instance specific distances using metric propagation. In ICML, pages 1407-1413, 2009.","title":"Learning instance specific distances using metric propagation","authors":"Ming De-Chuan Zhan, Yu-Feng Li, Zhi-Hua Li, Zhou","year":"2009","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zhan et al., 2016] De-Chuan Zhan, Peng Hu, Zui Chu, and Zhi- Hua Zhou. Learning expected hitting time distance. In AAAI, pages 2309-2314, 2016.","title":"Learning expected hitting time distance","authors":"Peng De-Chuan Zhan, Zui Hu, Zhi-Hua Chu, Zhou","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Zhang and Zhang, 2017] Jie Zhang and Lijun Zhang. Efficient stochastic optimization for low-rank distance metric learning. In AAAI, pages 933-940, 2017.","title":"Efficient stochastic optimization for low-rank distance metric learning","authors":"Zhang ; ] Jie Zhang, Lijun Zhang, Zhang","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}