Abstract
The majority of current methods in object classification use the one-against-rest training scheme. We argue that when applied to a large number of classes, this strategy is problematic: as the number of classes increases, the negative class becomes a very large and complicated collection of images. The resulting classification problem then becomes extremely unbalanced, and kernel SVM classifiers trained on such sets require long training time and are slow in prediction. To address these problems, we propose to consider the negative class as a background and characterize it by a prior distribution. Further, we propose to construct ”hybrid” classifiers, which are trained to separate this distribution from the samples of the positive class. A typical classifier first projects (by a function which may be non-linear) the inputs to a one-dimensional space, and then thresholds this projection. Theoretical results and empirical evaluation suggest that, after projection, the background has a relatively simple distribution, which is much easier to parameterize and work with. Our results show that hybrid classifiers offer an advantage over SVM classifiers, both in performance and complexity, especially when the negative (background) class is large.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: CVPR, pp. 2169–2178 (2006)
Grauman, K., Darrell, T.: The Pyramid Match Kernel: Efficient Learning with Sets of Features. JMLR 8, 725–760 (2007)
Maji, S., Berg, A.C., Malik, J.: Classification using intersection kernel support vector machines is efficient. In: CVPR, pp. 1–8 (2008)
Perronnin, F., Sánchez, J., Liu, Y.: Large-scale image categorization with explicit data embedding. In: CVPR, pp. 2297–2304 (2010)
Gehler, P., Nowozin, S.: On feature combination for multiclass object classification. In: Proc. of ICCV, pp. 221–228 (2009)
Song, Z., Chen, Q., Huang, Z., Hua, Y., Yan, S.: Contextualizing object detection and classification. In: CVPR, pp. 1585–1592 (2011)
Huang, Y., Huang, K., Yu, Y., Tan, T.: Salient coding for image classification. In: CVPR, pp. 1753–1760 (2011)
Rifkin, R., Klautau, A.: In defense of one-vs-all classification. JMLR 5, 101–141 (2004)
Akbani, R., Kwek, S.S., Japkowicz, N.: Applying Support Vector Machines to Imbalanced Datasets. In: Boulicaut, J.-F., Esposito, F., Giannotti, F., Pedreschi, D. (eds.) ECML 2004. LNCS (LNAI), vol. 3201, pp. 39–50. Springer, Heidelberg (2004)
Kotsiantis, S., Kanellopoulosâ, D.: Handling imbalanced datasets: A review (2006)
Steinwart, I.: Sparseness of support vector machines. JMLR 4, 1071–1105 (2003)
Zhang, J., Marszalek, M., Lazebnik, S., Schmid, C.: Local features and kernels for classification of texture and object categories: A comprehensive study. IJCV 73, 213–238 (2007)
Keerthi, S.S., Chapelle, O., DeCoste, D.: Building support vector machines with reduced classifier complexity. JMLR 7, 1493–1515 (2006)
Joachims, T., Finley, T., Yu, C.N.: Cutting-plane training of structural svms. Machine Learning 77, 27–59 (2009)
Osadchy, M., Keren, D.: Incorporating the boltzmann prior in object detection using svm. In: CVPR, pp. 2095–2101 (2006)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. of Computer Vision 60(2), 91–110 (2004)
Dance, C., Willamowski, J., Fan, L., Bray, C., Csurka, G.: Visual categorization with bags of keypoints. In: ECCV (2004)
Weiss, Y., Freeman, W.T.: What makes a good model of natural images. In: CVPR, pp. 1–8 (2007)
Zhu, S.C., Mumford, D.: Prior learning and gibbs reaction-diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 19, 1236–1250 (1997)
Roth, S., Black, M.J.: Fields of experts: A framework for learning image priors. In: CVPR, pp. 860–867 (2005)
Srivastava, A., Lee, A.B., Simoncelli, E.P., Zhu, S.-C.: On advances in statistical modeling of natural images. JMIV 18, 17–33 (2003)
Diaconis, P., Freedman, D.: Asymptotics of graphical projection pursuit. Ann. Statist. 12, 793–815 (1984)
Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset. T. R. 7694, California Institute of Technology (2007)
Lanckriet, G., Ghaoui, L., Bhattacharyya, C., Jordan, M.: A robust minimax approach to classification. JMLR 3, 555–582 (2002)
Smola, A.J., Schölkopf, B.: Sparse greedy matrix approximation for machine learning. In: ICML, pp. 911–918 (2000)
Tsai, D., Jing, Y., Liu, Y., Rowley, H., Ioffe, S., Rehg, J.M.: Large-scale image annotation using visual synset. In: ICCV (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Osadchy, M., Keren, D., Fadida-Specktor, B. (2012). Hybrid Classifiers for Object Classification with a Rich Background. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7576. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33715-4_21
Download citation
DOI: https://doi.org/10.1007/978-3-642-33715-4_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33714-7
Online ISBN: 978-3-642-33715-4
eBook Packages: Computer ScienceComputer Science (R0)