{"type":"ScholarlyArticle","title":"General Heterogeneous Transfer Distance Metric Learning via Knowledge Fragments Transfer","authors":[{"name":"Yong Luo","slug":"yong-luo","given":"Yong","family":"Luo","affiliation":"† School of Computer Science and Engineering , Nanyang Technological University , Singapore"},{"name":"Yonggang Wen","slug":"yonggang-wen","given":"Yonggang","family":"Wen","affiliation":"† School of Computer Science and Engineering , Nanyang Technological University , Singapore"},{"name":"Tongliang Liu","slug":"tongliang-liu","given":"Tongliang","family":"Liu","affiliation":"‡ UBTech Sydney AI Institute and SIT , FEIT , The University of Sydney , Australia"},{"name":"Dacheng Tao","slug":"dacheng-tao","given":"Dacheng","family":"Tao","affiliation":"‡ UBTech Sydney AI Institute and SIT , FEIT , The University of Sydney , Australia"}],"abstract":"Transfer learning aims to improve the performance of target learning task by leveraging information (or transferring knowledge) from other related tasks. Recently, transfer distance metric learning (TDML) has attracted lots of interests, but most of these methods assume that feature representations for the source and target learning tasks are the same. Hence, they are not suitable for the applications, in which the data are from heterogeneous domains (feature spaces, modalities and even semantics). Although some existing heterogeneous transfer learning (HTL) approaches is able to handle such domains, they lack flexibility in real-world applications, and the learned transformations are often restricted to be linear. We therefore develop a general and flexible heterogeneous TDML (HTDML) framework based on the knowledge fragment transfer strategy. In the proposed HTDML, any (linear or nonlinear) distance metric learning algorithms can be employed to learn the source metric beforehand. Then a set of knowledge fragments are extracted from the pre-learned source metric to help target metric learning. In addition, either linear or nonlinear distance metric can be learned for the target domain. Extensive experiments on both scene classification and object recognition demonstrate superiority of the proposed method.","doi":"10.24963/ijcai.2017/341","url":"https://ijcai.org/proceedings/2017/341","pdf":"https://ijcai.org/proceedings/2017/0341.pdf","markdown":"https://ijcai.org/proceedings/2017/341.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/341","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Machine Learning A-R","track":"Main track","number":341,"pages":{"first":2450,"last":2456},"keywords":["Machine Learning: Machine Learning","Machine Learning: Transfer, Adaptation, Multi-task Learning"],"videos":[],"references":[{"position":1,"raw":"[Chatfield et al., 2014] Ken Chatfield, Karen Simonyan, An- drea Vedaldi, and Andrew Zisserman. Return of the devil in the details: Delving deep into convolutional nets. arXiv preprint arXiv:1405.3531, 2014.","title":"Return of the devil in the details: Delving deep into convolutional nets","authors":"Ken Chatfield, Karen Simonyan, Andrea Vedaldi, Andrew Zisserman","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chua et al., 2009] Tat-Seng Chua, Jinhui Tang, Richang Hong, Haojie Li, Zhiping Luo, and Yantao Zheng. NUS- WIDE: a real-world web image database from national u- niversity of singapore. In CIVR, 2009.","title":"NUS-WIDE: a real-world web image database from national university of singapore","authors":"Tat-Seng Chua, Jinhui Tang, Richang Hong, Haojie Li, Zhiping Luo, Yantao Zheng","year":"2009","venue":"CIVR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Dai et al., 2015] Dengxin Dai, Till Kroeger, Radu Timofte, and Luc Van Gool. Metric imitation by manifold trans- fer for efficient vision applications. In IEEE CVPR, pages 3527-3536, 2015.","title":"Metric imitation by manifold transfer for efficient vision applications","authors":"Dai","year":"2015","venue":"IEEE CVPR","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, 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":"[Friedman, 2001] Jerome H Friedman. Greedy function ap- proximation: a gradient boosting machine. Annals of S- tatistics, pages 1189-1232, 2001.","title":"Greedy function approximation: a gradient boosting machine","authors":"Jerome H Friedman","year":"2001","venue":"Annals of Statistics","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hu et al., 2015] Junlin Hu, Jiwen Lu, and Yap-Peng Tan. Deep transfer metric learning. In IEEE CVPR, pages 325- 333, 2015.","title":"Deep transfer metric learning","authors":"Junlin Hu, Jiwen Lu, Yap-Peng Tan","year":"2015","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Isele et al., 2016] David Isele, Mohammad Rostami, and Eric Eaton. Using task features for zero-shot knowledge transfer in lifelong learning. In IJCAI, pages 1620-1626, 2016.","title":"Using task features for zero-shot knowledge transfer in lifelong learning","authors":"David Isele, Mohammad Rostami, Eric Eaton","year":"2016","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2016/232"},{"position":8,"raw":"[Kedem et al., 2012] Dor Kedem, Stephen Tyree, Fei Sha, Gert R Lanckriet, and Kilian Q Weinberger. Non-linear metric learning. In NIPS, pages 2573-2581, 2012.","title":"Non-linear metric learning","authors":"Dor Kedem, Stephen Tyree, Fei Sha, Gert R Lanckriet, Kilian Q Weinberger","year":"2012","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kulis, 2012] Brian Kulis. Metric learning: A survey. Foun- dations and Trends in Machine Learning, 5(4):287-364, 2012.","title":"Metric learning: A survey","authors":"Brian Kulis","year":"2012","venue":"Foundations and Trends in Machine Learning","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Lazebnik et al., 2006] Svetlana Lazebnik, Cordelia Schmid, and Jean Ponce. Beyond bags of features: Spatial pyra- mid matching for recognizing natural scene categories. In IEEE CVPR, pages 2169-2178, 2006.","title":"Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories","authors":"Svetlana Lazebnik, Cordelia Schmid, Jean Ponce","year":"2006","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Lim and Lanckriet, 2014] Daryl Lim and Gert Lanckriet. Efficient learning of mahalanobis metrics for ranking. In ICML, pages 1980-1988, 2014.","title":"Efficient learning of mahalanobis metrics for ranking","authors":"Daryl Lim, Gert Lanckriet","year":"2014","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Lin, 2007] Chih-Jen Lin. Projected gradient methods for nonnegative matrix factorization. Neural Computation, 19(10):2756-2779, 2007.","title":"Projected gradient methods for nonnegative matrix factorization","authors":"Chih-Jen Lin","year":"2007","venue":"Neural Computation","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liu and Tao, 2016] Tongliang Liu and Dacheng Tao. Clas- sification with noisy labels by importance reweighting. IEEE TPAMI, 38(3):447-461, 2016.","title":"Tongliang Liu and Dacheng Tao. Classification with noisy labels by importance reweighting","authors":"Tao Liu","year":"2016","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Liu et al., 2017] Tongliang Liu, Dacheng Tao, Mingli Song, and Stephen J Maybank. Algorithm-dependent gener- alization bounds for multi-task learning. IEEE TPAMI, 39(2):227-241, 2017.","title":"Algorithm-dependent generalization bounds for multi-task learning","authors":"Liu","year":"2017","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Lowe, 2004] D.G. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 60(2):91-110, 2004.","title":"Distinctive image features from scale-invariant keypoints","authors":"D G Lowe","year":"2004","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Luo et al., 2014] Yong Luo, Tongliang Liu, Dacheng Tao, and Chao Xu. Decomposition-based transfer distance metric learning for image classification. IEEE TIP, 23(9):3789-3801, 2014.","title":"Decomposition-based transfer distance metric learning for image classification","authors":"Yong Luo, Tongliang Liu, Dacheng Tao, Chao Xu","year":"2014","venue":"IEEE TIP","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Luo et al., 2016] Yong Luo, Yonggang Wen, and Dacheng Tao. On combining side information and unlabeled data for heterogeneous multi-task metric learning. In IJCAI, pages 1809-1815, 2016.","title":"On combining side information and unlabeled data for heterogeneous multi-task metric learning","authors":"Yong Luo, Yonggang Wen, Dacheng Tao","year":"2016","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2016/259"},{"position":18,"raw":"[Nesterov, 2005] Yu Nesterov. Smooth minimization of non-smooth functions. Mathematical Programming, 103(1):127-152, 2005.","title":"Smooth minimization of non-smooth functions","authors":"Yu Nesterov","year":"2005","venue":"Mathematical Programming","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Oliva and Torralba, 2001] A. Oliva and A. Torralba. Mod- eling the shape of the scene: A holistic representation of the spatial envelope. IJCV, 42(3):145-175, 2001.","title":"Modeling the shape of the scene: A holistic representation of the spatial envelope","authors":"A Oliva, A Torralba","year":"2001","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Pan and Yang, 2010] Sinno Jialin Pan and Qiang Yang. A survey on transfer learning. IEEE TKDE, 22(10):1345- 1359, 2010.","title":"A survey on transfer learning","authors":"Jialin Sinno, Qiang Pan, Yang","year":"2010","venue":"IEEE TKDE","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Qi et al., 2012] Guo-Jun Qi, Charu C Aggarwal, and Thomas S Huang. Transfer learning of distance metric- s by cross-domain metric sampling across heterogeneous spaces. In SDM, pages 528-539, 2012.","title":"Transfer learning of distance metrics by cross-domain metric sampling across heterogeneous spaces","authors":"Guo-Jun Qi, Charu C Aggarwal, Thomas S Huang","year":"2012","venue":"SDM","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Sokolova and Lapalme, 2009] Marina Sokolova and Guy Lapalme. A systematic analysis of performance measures for classification tasks. Information Processing and Man- agement, 45(4):427-437, 2009.","title":"A systematic analysis of performance measures for classification tasks","authors":"Lapalme Sokolova, Marina Sokolova, Guy Lapalme","year":"2009","venue":"Information Processing and Management","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Tao et al., 2007a] Dacheng Tao, Xuelong Li, Xindong Wu, Weiming Hu, and Stephen J Maybank. Supervised tensor learning. KIS, 13(1):1-42, 2007.","title":"Supervised tensor learning","authors":"Tao","year":"2007","venue":"KIS","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Tao et al., 2007b] Dacheng Tao, Xuelong Li, Xindong Wu, and Stephen J Maybank. General tensor discriminant anal- ysis and gabor features for gait recognition. IEEE TPAMI, 29(10):1700-1715, 2007.","title":"General tensor discriminant analysis and gabor features for gait recognition","authors":"Tao","year":"2007","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Tyree et al., 2011] Stephen Tyree, Kilian Q Weinberger, Kunal Agrawal, and Jennifer Paykin. Parallel boosted re- gression trees for web search ranking. In WWW, pages 387-396, 2011.","title":"Parallel boosted regression trees for web search ranking","authors":"Stephen Tyree, Q Kilian, Kunal Weinberger, Jennifer Agrawal, Paykin","year":"2011","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Vapnik and Izmailov, 2015] Vladimir Vapnik and Rauf Iz- mailov. Learning using privileged information: Similari- ty control and knowledge transfer. JMLR, 16:2023-2049, 2015.","title":"Learning using privileged information: Similarity control and knowledge transfer","authors":"Izmailov Vapnik","year":"2015","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wang and Mahadevan, 2011] Chang Wang and Sridhar Ma- hadevan. Heterogeneous domain adaptation using mani- fold alignment. In IJCAI, pages 1541-1546, 2011.","title":"Heterogeneous domain adaptation using manifold alignment","authors":"Chang Wang, Sridhar Mahadevan","year":"2011","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2011/259"},{"position":28,"raw":"[Weinberger et al., 2005] Kilian Q Weinberger, John Blitzer, and Lawrence K Saul. Distance metric learning for large margin nearest neighbor classification. In NIPS, pages 1473-1480, 2005.","title":"Distance metric learning for large margin nearest neighbor classification","authors":"John Kilian Q Weinberger, Lawrence K Blitzer, Saul","year":"2005","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Xu et al., 2014] Chang Xu, Dacheng Tao, and Chao Xu. Large-margin multi-view information bottleneck. IEEE T- PAMI, 36(8):1559-1572, 2014.","title":"Large-margin multi-view information bottleneck","authors":"Chang Xu, Dacheng Tao, Chao Xu","year":"2014","venue":"IEEE T-PAMI","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Xu et al., 2015] Chang Xu, Dacheng Tao, and Chao X- u. Multi-view intact space learning. IEEE TPAMI, 37(12):2531-2544, 2015.","title":"Multi-view intact space learning","authors":"Chang Xu, Dacheng Tao, Chao Xu","year":"2015","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhang and Yeung, 2011] Yu Zhang and Dit-Yan Yeung. Multi-task learning in heterogeneous feature spaces. In AAAI, pages 574-579, 2011.","title":"Multi-task learning in heterogeneous feature spaces","authors":"Yeung Zhang, Yu Zhang, Dit-Yan Yeung","year":"2011","venue":"AAAI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}