iccv iccv2013 iccv2013-248 iccv2013-248-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Viktoriia Sharmanska, Novi Quadrianto, Christoph H. Lampert
Abstract: Many computer visionproblems have an asymmetric distribution of information between training and test time. In this work, we study the case where we are given additional information about the training data, which however will not be available at test time. This situation is called learning using privileged information (LUPI). We introduce two maximum-margin techniques that are able to make use of this additional source of information, and we show that the framework is applicable to several scenarios that have been studied in computer vision before. Experiments with attributes, bounding boxes, image tags and rationales as additional information in object classification show promising results.
[1] H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool. Speeded-up robust features (SURF). CVIU, 2008.
[2] R. Bekkerman and J. Jeon. Multi-modal clustering for multimedia collections. In CVPR, 2007.
[3] M. B. Blaschko and C. H. Lampert. Correlational spectral clustering. In CVPR, 2008.
[4] O. Chapelle. Training a support vector machine in the primal. Neural Computation, pages 1155–1 178, 2007.
[5] C. M. Christoudias, R. Urtasun, and T. Darrell. Multi-view learning in the presence of view disagreement. In UAI, 2008.
[6] C. Dance, J. Willamowski, L. Fan, C. Bray, and G. Csurka. Visual categorization with bags of keypoints. In ECCV, 2004.
[7] J. Donahue and K. Grauman. Annotator rationales for visual recognition. In ICCV, 2011.
[8] M. Everingham, L. J. V. Gool, C. K. I. Williams, J. M. Winn, and A. Zisserman. The Pascal VOC challenge. IJCV, 2010.
[9] R.-E. Fan, K.-W. Chang, C.-J. Hsieh, X.-R. Wang, and C.-J. Lin. LIBLINEAR: A library for large linear classification. JMLR, 2008.
[10] P. Gehler and S. Nowozin. On feature combination for multiclass object classification. In ICCV, 2009.
[11] T. Joachims. Making large-scale SVM learning practical. In Advances in kernel methods, pages 169–184, 1999.
[12] T. Joachims. Optimizing search engines using clickthrough data. In KDD, 2002.
[13] D. Kuettel, M. Guillaumin, and V. Ferrari. Segmentation propagation in ImageNet. In ECCV, 2012.
[14] C. H. Lampert, H. Nickisch, and S. Harmeling. Attribute-based classification for zero-shot visual object categorization. PAMI, 2013.
[15] M. Lapin, M. Hein, and B. Schiele. Learning using privileged information: SVM+ and weighted SVM, 2013. arXiv: 1306.3161 [stat.ML].
[16] O. Maron and A. L. Ratan. Multiple-instance learning for natural scene classification. In ICML, 1998.
[17] D. Pechyony and V. Vapnik. On the theory oflearning with privileged information. In NIPS, 2010.
[18] D. Pechyony and V. Vapnik. Fast optimization algorithms for solving SVM+. In Stat. Learning and Data Science, 2011.
[19] F. Perronnin, J. S ´anchez, and T. Mensink. Improving fisher kernel for large-scale image classification. In ECCV, 2010.
[20] N. Quadrianto and C. H. Lampert. Learning multi-view neighborhood preserving projections. In ICML, 2011.
[21] B. Sch o¨lkopf and A. Smola. Learning with Kernels. MIT Press, 2002.
[22] S. Shalev-Shwartz, Y. Singer, and N. Srebro. Pegasos: Primal estimated sub-gradient solver for SVM. In ICML, 2007.
[23] C. G. Snoek, M. Worring, and A. W. Smeulders. Early versus late fusion in semantic video analysis. In ACM MM, 2005.
[24] V. Vapnik. The nature of statistical learning theory. Springer, 1999.
[25] V. Vapnik and A. Vashist. A new learning paradigm: Learning using privileged information. Neural Networks, 2009.
[26] A. Vedaldi, V. Gulshan, M. Varma, and A. Zisserman. Multiple kernels for object detection. In ICCV, 2009.
[27] Y. Wang and G. Mori. A discriminative latent model of object classes and attributes. In ECCV, 2010.
[28] O. F. Zaidan and J. Eisner. Modeling annotators: A generative approach to learning from annotator rationales. In Conference on Empirical Methods in Natural Language Processing, 2008. 883322