Max-Margin Dictionary Learning for Multiclass Image Categorization

  • Xiao-Chen Lian
  • Zhiwei Li
  • Bao-Liang Lu
  • Lei Zhang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6314)

Abstract

Visual dictionary learning and base (binary) classifier training are two basic problems for the recently most popular image categorization framework, which is based on the bag-of-visual-terms (BOV) models and multiclass SVM classifiers. In this paper, we study new algorithms to improve performance of this framework from these two aspects. Typically SVM classifiers are trained with dictionaries fixed, and as a result the traditional loss function can only be minimized with respect to hyperplane parameters (w and b). We propose a novel loss function for a binary classifier, which links the hinge-loss term with dictionary learning. By doing so, we can further optimize the loss function with respect to the dictionary parameters. Thus, this framework is able to further increase margins of binary classifiers, and consequently decrease the error bound of the aggregated classifier. On two benchmark dataset, Graz [1] and the fifteen scene category dataset [2], our experiment results significantly outperformed state-of-the-art works.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Fulkerson, B., Vedaldi, A., Soatto, S.: Localizing objects with smart dictionaries. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 179–192. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  2. 2.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: Proc. CVPR, pp. 2169–2178 (2006)Google Scholar
  3. 3.
    Wu, J., Rehg, J.: Where am I: Place instance and category recognition using spatial PACT. In: Proc. CVPR (2008)Google Scholar
  4. 4.
    Yang, J., Yu, K., Gong, Y., Huang, T.: Linear spatial pyramid matching using sparse coding for image classification. In: Proc. CVPR (2009)Google Scholar
  5. 5.
    Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: Proc. CVPR, vol. 2, pp. 524–531Google Scholar
  6. 6.
    Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. Comput. Vis. Image Underst. 106, 59–70 (2007)CrossRefGoogle Scholar
  7. 7.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge, Results (2009), http://www.pascal-network.org/challenges/VOC/voc2009/workshop/index.html
  8. 8.
    Sivic, J., Zisserman, A.: Video Google: A text retrieval approach to object matching in videos. In: Proc. ICCV., vol. 2, pp. 1470–1477 (2003)Google Scholar
  9. 9.
    Jiang, Y.G., Ngo, C.W.: Visual word proximity and linguistics for semantic video indexing and near-duplicate retrieval. Comput. Vis. Image Underst. 113, 405–414 (2009)CrossRefGoogle Scholar
  10. 10.
    Platt, J., Cristianini, N., Shawe-Taylor, J.: Large margin DAGs for multiclass classification. Advances in neural information processing systems 12, 547–553 (2000)Google Scholar
  11. 11.
    Zhang, W., Surve, A., Fern, X., Dietterich, T.: Learning non-redundant codebooks for classifying complex objects. In: Proceedings of the 26th Annual International Conference on Machine Learning (2009)Google Scholar
  12. 12.
    Perronnin, F.: Universal and adapted vocabularies for generic visual categorization. IEEE Transactions on Pattern Analysis and Machine Intelligence 30, 1243–1256 (2008)CrossRefGoogle Scholar
  13. 13.
    Winn, J., Criminisi, A., Minka, T.: Object categorization by learned universal visual dictionary. In: Proc. ICCV, pp. 1800–1807 (2005)Google Scholar
  14. 14.
    Lazebnik, S., Raginsky, M.: Supervised learning of quantizer codebooks by information loss minimization. IEEE Trans. Pattern Anal. Mach. Intell. 31, 1294–1309 (2009)CrossRefGoogle Scholar
  15. 15.
    Moosmann, F., Triggs, B., Jurie, F.: Fast discriminative visual codebooks using randomized clustering forests. Advances in neural information processing systems 19, 985 (2007)Google Scholar
  16. 16.
    Shotton, J., Johnson, J., Cipolla, M.: Semantic texton forests for image categorization and segmentation. In: Proc. CVPR (2008)Google Scholar
  17. 17.
    Mairal, J., Bach, F., Ponce, J., Sapiro, G., Zisserman, A.: Supervised dictionary learning. Advances in Neural Information Processing Systems 21 (2009)Google Scholar
  18. 18.
    Mairal, J., Bach, F., Ponce, J., Sapiro, G., Zisserman, A.: Discriminative learned dictionaries for local image analysis. In: Proc. CVPR (2008)Google Scholar
  19. 19.
    Huang, K., Aviyente, S.: Sparse representation for signal classification. Advances in Neural Information Processing Systems 19, 609 (2007)Google Scholar
  20. 20.
    Yang, J., Yu, K., Huang, T.: Supervised Translation-Invariant Sparse Coding. In: Proc. CVPR (2010)Google Scholar
  21. 21.
    Boureau, Y., Bach, F., LeCun, Y., Ponce, J.: Learning Mid-Level Features For Recognition. In: Proc. CVPR (2010)Google Scholar
  22. 22.
    Lowe, D.: Object recognition from local scale-invariant features. In: Proc. ICCV., vol. 2, pp. 1150–1157 (1999)Google Scholar
  23. 23.
    Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Lost in quantization: Improving particular object retrieval in large scale image databases. In: Proc. CVPR (2008)Google Scholar
  24. 24.
    Shor, N., Kiwiel, K., Ruszcayǹski, A.: Minimization methods for non-differentiable functions. Springer, New York (1985)MATHGoogle Scholar
  25. 25.
    Allwein, E., Schapire, R., Singer, Y.: Reducing multiclass to binary: A unifying approach for margin classifiers. The Journal of Machine Learning Research 1, 113–141 (2001)MATHCrossRefMathSciNetGoogle Scholar
  26. 26.
    Uijlings, J., Smeulders, A., Scha, R.: What is the Spatial Extent of an Object? In: Proc. CVPR (2009)Google Scholar
  27. 27.
    Zhou, X., Cui, N., Li, Z., Liang, F., Huang, T.: Hierarchical Gaussianization for Image Classification. In: Proc. ICCV (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Xiao-Chen Lian
    • 1
  • Zhiwei Li
    • 3
  • Bao-Liang Lu
    • 1
    • 2
  • Lei Zhang
    • 3
  1. 1.Dept. of Computer Science and EngineeringShanghai Jiao Tong UniversityChina
  2. 2.MOE-MS Key Lab for BCMIShanghai Jiao Tong UniversityChina
  3. 3.Microsoft Research Asia 

Personalised recommendations