Abstract
Multiple Kernel Learning (MKL) has become a preferred choice for information fusion in image recognition problem. Aim of MKL is to learn optimal combination of kernels formed from different features, thus, to learn importance of different feature spaces for classification. Augmented Kernel Matrix (AKM) has recently been proposed to accommodate for the fact that a single training example may have different importance in different feature spaces, in contrast to MKL that assigns same weight to all examples in one feature space. However, AKM approach is limited to small datasets due to its memory requirements.
We propose a novel two stage technique to make AKM applicable to large data problems. In first stage various kernels are combined into different groups automatically using kernel alignment. Next, most influential training examples are identified within each group and used to construct an AKM of significantly reduced size. This reduced size AKM leads to same results as the original AKM. We demonstrate that proposed two stage approach is memory efficient and leads to better performance than original AKM and is robust to noise. Results are compared with other state-of-the art MKL techniques, and show improvement on challenging object recognition benchmarks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Schölkopf, B., Smola, A.: Learning with Kernels. MIT Press, Cambridge (2002)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, Heidelberg (2000)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. PAMI 27(10), 1615–1630 (2005)
van de Sande, K., Gevers, T., Snoek, C.: Evaluation of color descriptors for object and scene recognition. In: CVPR (2008)
Lanckriet, G., Cristianini, N., Bartlett, P., Ghaoui, L., Jordan, M.: Learning the Kernel Matrix with Semidefinite Programming. JMLR 5, 27–72 (2004)
Bach, F., Lanckriet, G., Jordan, M.: Multiple Kernel Learning, Conic Duality, and the SMO Algorithm. In: ICML (2004)
Sonnenburg, S., Rätsch, G., Schafer, C., Schölkopf, B.: Large Scale Multiple Kernel Learning. JMLR 7, 1531–1565 (2006)
Yan, F., Mikolajczyk, K., Kittler, J., Tahir, M.A.: Combining multiple kernels by augmenting the kernel matrix. In: El Gayar, N., Kittler, J., Roli, F. (eds.) MCS 2010. LNCS, vol. 5997, pp. 175–184. Springer, Heidelberg (2010)
Szafranski, M., Grandvalet, Y., Rakotomamonjy, A.: Composite Kernel Learning. ML 79(1), 73–103 (2010)
Nath, J., Dinesh, G., Raman, S., Bhattacharyya, C., Ben-Tal, A., Ramakrishnan, K.: On the Algorithmics and Applications of a Mixed-norm Based Kernel Learning Formulation. In: NIPS (2009)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCALVisual Object Classes Challenge ( VOC 2007)Results (2007) http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html
M. Nilsback A. Zisserman.: A visual Vocabulary for Flower Classification. In: CVPR, 2006.
Nilsback, M.-E., Zisserman, A.: Automated Flower Classification over a Large Number of Classes. In: ICCVGIP (2008)
Kloft, M., Brefeld, U., Laskov, P., Sonnenburg, S.: Nonsparse Multiple Kernel Learning. In: NIPS Workshop on Kernel Learning: Automatic Selection of Optimal Kernels (2008)
Schölkopf, B., Mika, S., Burges, C., Knirsch, P., Müller, K., Rätsch, G., Smola, A.: Input Space Versus Feature Space in Kernel-Based Methods. NN 10(5), 1000–1017 (1999)
Cristianini, N., Shawe-Taylor, J., Elisseeff, A., Kandola, J.: On Kernel-Target Alignment. In: NIPS (2001)
Lawrence, N., Sanguinetti, G.: Matching Kernel through Kullback-Leibler Divergence Minimisation. Technical Report CS-04-12, Department of Computer Science, University of Sheffield (2005)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories. In: CVPR (2006)
Gehler, P., Nowozin, S.: On Feature Combination for Multiclass Object Classification. In: ICCV (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Awais, M., Yan, F., Mikolajczyk, K., Kittler, J. (2011). Two-Stage Augmented Kernel Matrix for Object Recognition. In: Sansone, C., Kittler, J., Roli, F. (eds) Multiple Classifier Systems. MCS 2011. Lecture Notes in Computer Science, vol 6713. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21557-5_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-21557-5_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21556-8
Online ISBN: 978-3-642-21557-5
eBook Packages: Computer ScienceComputer Science (R0)