cvpr cvpr2013 cvpr2013-179 cvpr2013-179-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Ilja Kuzborskij, Francesco Orabona, Barbara Caputo
Abstract: Since the seminal work of Thrun [17], the learning to learnparadigm has been defined as the ability ofan agent to improve its performance at each task with experience, with the number of tasks. Within the object categorization domain, the visual learning community has actively declined this paradigm in the transfer learning setting. Almost all proposed methods focus on category detection problems, addressing how to learn a new target class from few samples by leveraging over the known source. But if one thinks oflearning over multiple tasks, there is a needfor multiclass transfer learning algorithms able to exploit previous source knowledge when learning a new class, while at the same time optimizing their overall performance. This is an open challenge for existing transfer learning algorithms. The contribution of this paper is a discriminative method that addresses this issue, based on a Least-Squares Support Vector Machine formulation. Our approach is designed to balance between transferring to the new class and preserving what has already been learned on the source models. Exten- sive experiments on subsets of publicly available datasets prove the effectiveness of our approach.
[1] Y. Aytar and A. Zisserman. Tabula rasa: Model transfer for object category detection. In Proc. ICCV, 2011.
[2] J. Blitzer, R. McDonald, and F. Pereira. Domain adaptation with structural correspondence learning. In Proc. EMNLP, pages 120–128. ACL, 2006.
[3] S. Boyd and L. Vandenberghe. Convex optimization. Cambridge university press, 2004.
[4] G. Cawley. Leave-one-out cross-validation based model selection criteria for weighted LS-SVMs. In Proc. IJCNN, 2006.
[5] K. Crammer and Y. Singer. On the algorithmic implementation of multiclass kernel-based vector machines. JMLR, 2:265–292, 2002.
[6] H. Daum e´. Frustratingly easy domain adaptation. In Anual meeting, ACL, 2007.
[7] L. Duan, D. Xu, I. Tsang, and J. Luo. Visual event recognition in videos by learning from web data. IEEE TPAMI, 34(9): 1667–1680, 2012.
[8] P. Gehler and S. Nowozin. On feature combination for multiclass object classification. In Proc. ICCV, 2009.
[9] G. Griffin, A. Holub, and P. Perona. Caltech-256 object category dataset. Technical report, Caltech, 2007.
[10] D. Hush, P. Kelly, C. Scovel, and I. Steinwart. QP algorithms with guaranteed accuracy and run time for support vector machines. JMLR, 7:733–769, 2006.
[11] L. Jie, T. Tommasi, and B. Caputo. Multiclass transfer learning from unconstrained priors. In Proc. ICCV, pages 1863– 1870. IEEE, 2011.
[12] I. Kuzborskij and F. Orabona. Stability and hypothesis transfer learning. In Proc. ICML, 2013.
[13] C. Lampert, H. Nickisch, and S. Harmeling. Learning to detect unseen object classes by between-class attribute transfer. In Proc. CVPR, pages 951–958. IEEE, 2009.
[14] A. Lazaric, M. Restelli, and A. Bonarini. Transfer of samples in batch reinforcement learning. In Proc. ICML, 2008.
[15] Y. Mansour, M. Mohri, and A. Rostamizadeh. Domain adaptation with multiple sources. Proc. NIPS, 21:1041–1048, 2009.
[16] J. Suykens and J. Vandewalle. Least squares support vector machine classifiers. Neural Process. Lett., 9(3), 1999.
[17] S. Thrun. Is learning the n-th thing any easier than learning the first? In Proc. NIPS, pages 640–646, 1995.
[18] T. Tommasi, F. Orabona, and B. Caputo. Safety in numbers: Learning categories from few examples with multi model knowledge transfer. In Proc. CVPR, pages 3081– 3088. IEEE, 2010.
[19] J. Yang, R. Yan, and A. Hauptmann. Cross-domain video concept detection using adaptive SVMs. In Proc. ACM, pages 188–197. ACM, 2007.
[20] Y. Yao and G. Doretto. Boosting for transfer learning with multiple sources. In Proc. CVPR, 2010. 333333666533