A Multiple Kernel Learning Approach to Joint Multi-class Object Detection

  • Christoph H. Lampert
  • Matthew B. Blaschko
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5096)

Abstract

Most current methods for multi-class object classification and localization work as independent 1-vs-rest classifiers. They decide whether and where an object is visible in an image purely on a per-class basis. Joint learning of more than one object class would generally be preferable, since this would allow the use of contextual information such as co-occurrence between classes. However, this approach is usually not employed because of its computational cost.

In this paper we propose a method to combine the efficiency of single class localization with a subsequent decision process that works jointly for all given object classes. By following a multiple kernel learning (MKL) approach, we automatically obtain a sparse dependency graph of relevant object classes on which to base the decision. Experiments on the PASCAL VOC 2006 and 2007 datasets show that the subsequent joint decision step clearly improves the accuracy compared to single class detection.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bay, H., Tuytelaars, T., Gool, L.J.V.: SURF: Speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 404–417. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  2. 2.
    Bergtholdt, M., Kappes, J.H., Schnörr, C.: Learning of graphical models and efficient inference for object class recognition. In: Franke, K., Müller, K.-R., Nickolay, B., Schäfer, R. (eds.) DAGM 2006. LNCS, vol. 4174, pp. 273–283. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  3. 3.
    Biederman, I.: Recognition by components - a theory of human image understanding. Psychological Review 94(2), 115–147 (1987)CrossRefGoogle Scholar
  4. 4.
    Biederman, I., Mezzanotte, R.J., Rabinowitz, J.C.: Scene perception: Detecting and judging objects undergoing relational violations. Cognitive Psychology 14, 143–177 (1982)CrossRefGoogle Scholar
  5. 5.
    Bosch, A., Zisserman, A., Muñoz, X.: Representing shape with a spatial pyramid kernel. In: CIVR, pp. 401–408 (2007)Google Scholar
  6. 6.
    Chum, O., Zisserman, A.: An exemplar model for learning object classes. In: CVPR, pp. 1–8 (2007)Google Scholar
  7. 7.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893 (2005)Google Scholar
  8. 8.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2007 Results (2007), http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html
  9. 9.
    Everingham, M., Zisserman, A., Williams, C.K.I., Van Gool, L.: The PASCAL Visual Object Classes Challenge 2006 Results (2006), http://www.pascal-network.org/challenges/VOC/voc2006/results.pdf
  10. 10.
    Fergus, R., Perona, P., Zisserman, A.: A sparse object category model for efficient learning and exhaustive recognition. In: CVPR, pp. 380–387 (2005)Google Scholar
  11. 11.
    Ferrari, V., Fevrier, L., Jurie, F., Schmid, C.: Groups of adjacent contour segments for object detection. PAMI 30, 36–51 (2008)Google Scholar
  12. 12.
    Fritz, M., Leibe, B., Caputo, B., Schiele, B.: Integrating representative and discriminative models for object category detection. In: ICCV, pp. 1363–1370 (2005)Google Scholar
  13. 13.
    Keysers, D., Deselaers, T., Breuel, T.M.: Optimal geometric matching for patch-based object detection. ELCVIA 6(1), 44–54 (2007)Google Scholar
  14. 14.
    Kienzle, W., Bakır, G.H., Franz, M.O., Schölkopf, B.: Face detection - efficient and rank deficient. In: NIPS (2004)Google Scholar
  15. 15.
    Lampert, C.H., Blaschko, M.B., Hofmann, T.: Beyond sliding windows: Object localization by efficient subwindow search. In: CVPR (2008)Google Scholar
  16. 16.
    Lanckriet, G.R.G., Cristianini, N., Bartlett, P., Ghaoui, L.E., Jordan, M.I.: Learning the kernel matrix with semidefinite programming. JMLR 5, 27–72 (2004)Google Scholar
  17. 17.
    Lienhart, R., Liang, L., Kuranov, A.: A detector tree of boosted classifiers for real-time object detection and tracking. ICME 2, 277–280 (2003)Google Scholar
  18. 18.
    Ommer, B., Buhmann, J.M.: Learning the compositional nature of visual objects. In: CVPR (2007)Google Scholar
  19. 19.
    Opelt, A., Pinz, A., Fussenegger, M., Auer, P.: Generic object recognition with boosting. PAMI 28(3), 416–431 (2006)Google Scholar
  20. 20.
    Rabinovich, A., Vedaldi, A., Galleguillos, C., Wiewiora, E., Belongie, S.: Objects in context. In: ICCV (2007)Google Scholar
  21. 21.
    Schölkopf, B., Smola, A.J.: Learning with Kernels. MIT Press, Cambridge (2002)Google Scholar
  22. 22.
    Schulz, W., Enzweiler, M., Ehlgen, T.: Pedestrian recognition from a moving catadioptric camera. In: Hamprecht, F.A., Schnörr, C., Jähne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 456–465. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  23. 23.
    Sonnenburg, S., Rätsch, G., Schäfer, C., Schölkopf, B.: Large scale multiple kernel learning. JMLR 7, 1531–1565 (2006)Google Scholar
  24. 24.
    Teynor, A., Burkhardt, H.: Patch based localization of visual object class instances. In: MVA (2007)Google Scholar
  25. 25.
    Torralba, A.: Contextual priming for object detection. IJCV 53(2), 169–191 (2003)CrossRefGoogle Scholar
  26. 26.
    Torralba, A., Murphy, K.P., Freeman, W.T.: Shared features for multiclass object detection. In: Toward Category-Level Object Recognition, pp. 345–361 (2006)Google Scholar
  27. 27.
    Torralba, A., Oliva, A.: Statistics of natural image categories. Network: Computation in Neural Systems 14(3), 391–412 (2003)CrossRefGoogle Scholar
  28. 28.
    Viola, P.A., Jones, M.J.: Robust real-time face detection. IJCV 57(2), 137–154 (2004)CrossRefGoogle Scholar
  29. 29.
    Zhang, J., Marszalek, M., Lazebnik, S., Schmid, C.: Local features and kernels for classification of texture and object categories: A comprehensive study. IJCV 73(2), 213–238 (2007)CrossRefGoogle Scholar
  30. 30.
    Zien, A., Ong, C.S.: Multiclass multiple kernel learning. In: ICML, pp. 1191–1198 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Christoph H. Lampert
    • 1
  • Matthew B. Blaschko
    • 1
  1. 1.Department for Empirical InferenceMax Planck Institute for Biological CyberneticsTübingenGermany

Personalised recommendations