Efficient Classification of Images with Taxonomies

  • Alexander Binder
  • Motoaki Kawanabe
  • Ulf Brefeld
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5996)


We study the problem of classifying images into a given, pre-determined taxonomy. The task can be elegantly translated into the structured learning framework. Structured learning, however, is known for its memory consuming and slow training processes. The contribution of our paper is twofold: Firstly, we propose an efficient decomposition of the structured learning approach into an equivalent ensemble of local support vector machines (SVMs) which can be trained with standard techniques. Secondly, we combine the local SVMs to a global model by re-incorporating the taxonomy into the training process. Our empirical results on Caltech256 and VOC2006 data show that our local-global SVM effectively exploits the structure of the taxonomy and outperforms multi-class classification approaches.


Support Vector Machine Training Image Neural Information Processing System Taxonomy Information Spatial Pyramid Match 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Marszalek, M., Schmid, C.: Constructing category hierarchies for visual recognition. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 479–491. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  2. 2.
    Lampert, C.H., Blaschko, M.B.: A multiple kernel learning approach to joint multi-class object detection. In: Proceedings of the 30th DAGM symposium on Pattern Recognition (2008)Google Scholar
  3. 3.
    Blaschko, M.B., Gretton, A.: Learning taxonomies by dependence maximization. In: Advances in Neural Information Processing Systems (2009)Google Scholar
  4. 4.
    Tibshirani, R., Hastie, T.: Margin trees for high-dimensional classification. JMLR 8, 637–652 (2007)Google Scholar
  5. 5.
    Marszalek, M., Schmid, C.: Semantic hierarchies for visual object recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2007)Google Scholar
  6. 6.
    Taskar, B., Guestrin, C., Koller, D.: Max–margin Markov networks. In: Advances in Neural Information Processing Systems (2004)Google Scholar
  7. 7.
    Tsochantaridis, I., Joachims, T., Hofmann, T., Altun, Y.: Large margin methods for structured and interdependent output variables. Journal of Machine Learning Research 6, 1453–1484 (2005)MathSciNetGoogle Scholar
  8. 8.
    Cai, L., Hofmann, T.: Hierarchical document categorization with support vector machines. In: Proceedings of the Conference on Information and Knowledge Management (2004)Google Scholar
  9. 9.
    Lafferty, J., Zhu, X., Liu, Y.: Kernel conditional random fields: representation and clique selection. In: Proceedings of the International Conference on Machine Learning (2004)Google Scholar
  10. 10.
    Weston, J., Watkins, C.: Multi–class support vector machines. Technical Report CSD-TR-98-04, Department of Computer Sciences, Royal Holloway, University of London (1998)Google Scholar
  11. 11.
    Har-Peled, S., Roth, D., Zimak, D.: Constraint classification for multi–class classification and ranking. In: Advances in Neural Information Processing Systems (2002)Google Scholar
  12. 12.
    Brefeld, U., Geibel, P., Wysotzki, F.: Support vector machines with example dependent costs. In: Lavrač, N., Gamberger, D., Todorovski, L., Blockeel, H. (eds.) ECML 2003. LNCS (LNAI), vol. 2837, pp. 23–34. Springer, Heidelberg (2003)Google Scholar
  13. 13.
    Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset. Technical Report 7694, California Institute of Technology (2007)Google Scholar
  14. 14.
    Everingham, M., Zisserman, A., Williams, C.K.I., Gool, L.V.: The 2006 pascal visual object classes challenge (voc2006) results (2006)Google Scholar
  15. 15.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, USA, June 2006, vol. 2, pp. 2169–2178 (2006)Google Scholar
  16. 16.
    Csurka, G., Bray, C., Dance, C., Fan, L.: Visual categorization with bags of keypoints. In: Workshop on Statistical Learning in Computer Vision, ECCV, Prague, Czech Republic, May 2004, pp. 1–22 (2004)Google Scholar
  17. 17.
    Lowe, D.: Distinctive image features from scale invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  18. 18.
    Zhang, J., Marszalek, M., Lazebnik, S., Schmid, C.: Local features and kernels for classification of texture and object categories: A comprehensive study. International Journal of Computer Vision 73(2), 213–238 (2007)CrossRefGoogle Scholar
  19. 19.
    Griffin, G., Perona, P.: Learning and using taxonomies for fast visual categorization. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Alexander Binder
    • 1
  • Motoaki Kawanabe
    • 1
    • 2
  • Ulf Brefeld
    • 2
  1. 1.Fraunhofer Institute FIRSTBerlinGermany
  2. 2.TU BerlinBerlinGermany

Personalised recommendations