Advertisement

Efficient Learning of Relational Object Class Models

  • Aharon Bar-HillelEmail author
  • Daphna Weinshall
Article

Abstract

We present an efficient method for learning part-based object class models from unsegmented images represented as sets of salient features. A model includes parts’ appearance, as well as location and scale relations between parts. The object class is generatively modeled using a simple Bayesian network with a central hidden node containing location and scale information, and nodes describing object parts. The model’s parameters, however, are optimized to reduce a loss function of the training error, as in discriminative methods. We show how boosting techniques can be extended to optimize the relational model proposed, with complexity linear in the number of parts and the number of features per image. This efficiency allows our method to learn relational models with many parts and features. The method has an advantage over purely generative and purely discriminative approaches for learning from sets of salient features, since generative method often use a small number of parts and features, while discriminative methods tend to ignore geometrical relations between parts. Experimental results are described, using some bench-mark data sets and three sets of newly collected data, showing the relative merits of our method in recognition and localization tasks.

Keywords

Object class recognition Object localization Generative models Boosting Weakly supervised learning 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Agarwal, S., Awan, A., & Roth, D. (2004). Learning to detect objects in images via a sparse, part based representation. Pattern Analysis and Machine Intelligence, 20(11), 1475–1490. CrossRefGoogle Scholar
  2. Agarwal, S., & Roth, D. (2002). Learning a sparse representation for object detection. In ECCV (pp. 113–130). Google Scholar
  3. Bar-Hillel, A., Hertz, T., & Weinshall, D. (2005a). Efficient learning of relational object class models. In ICCV. Google Scholar
  4. Bar-Hillel, A., Hertz, T., & Weinshall, D. (2005b). Object class recognition by boosting a part based model. In CVPR. Los Alamitos: IEEE Computer Society Google Scholar
  5. Borenstein, E., Sharon, E., & Ullman, S. (2004). Combining top-down and bottom-up segmentation. In IEEE workshop on perceptual organization in computer vision (CVPR). Google Scholar
  6. Chan, A. B., Vasconcelos, N., & Moreno, P. J. (2004). A family of probabilistic kernels based on information divergence. Google Scholar
  7. Csurka, G., Bray, C., Dance, C., & Fan, L. (2004). Visual categorization with bags of keypoints. In ECCV. Google Scholar
  8. Dorkó, G., & Schmid, C. (2005, submitted). Object class recognition using discriminative local features. IEEE Transactions on Pattern Analysis and Machine Intelligence. Google Scholar
  9. Everingham, M. R., Zisserman, A., Williams, C. K. I., & Van Gool, L. et al. (2006). The 2005 pascal visual object classes challenge. In J. Quinonero-Candela, I. Dagan, B. Magnini, & F. d’Alche-Buc (Eds.), LNAI: Vol. 3944. Machine learning challenges. Evaluating predictive uncertainty, visual object classification, and recognising textual entailment (pp. 117–176). Google Scholar
  10. Fei-Fei, L., Fergus, R., & Perona, P. (2003). A bayesian approach to unsupervised one shot learning of object catgories. In ICCV. Google Scholar
  11. Feltzenswalb, P., & Huttenlocher, D. (2005). Pictorial structures for object recognition. International Journal of Computer Vision, 61, 55–79. CrossRefGoogle Scholar
  12. Fergus, R., Perona, P., & Zisserman, A. (2003). Object class recognition by unsupervised scale invariant learning. In CVPR. Los Alamitos: IEEE Computer Society Google Scholar
  13. Fergus, R., Perona, P., & Zisserman, A. (2005). A sparse object category model for efficient learning and exhaustive recognition. In CVPR. Google Scholar
  14. Freund, Y., & Schapire, R. E. (1996). Experiments with a new boosting algorithm. In ICML (pp. 148–156). Google Scholar
  15. Friedman, J. H., Hastie, T., & Tibshirani, R. (2000). Additive logistic regression: a statistical view ofboosting. Annals of Statistics, 28, 337–407. zbMATHCrossRefMathSciNetGoogle Scholar
  16. Fritz, M., Leibe, B., Caputo, B., & Schiele, B. (2005). Integrating representative and discriminant models for object category detection. In ICCV. Google Scholar
  17. Gao, D., & Vasconcelos, N. (2004). Discriminant saliency for visual recognition from cluttered scenes. In NIPS. Google Scholar
  18. Holub, A. D., & Perona, P. (2005). A discriminative framework for modeling object classes. In CVPR. Google Scholar
  19. Holub, A. D., Welling, M., & Perona, P. (2005). Combining generative models and fisher kernels for object class recognition. In ICCV. Google Scholar
  20. Kadir, T., & Brady, M. (2001). Scale, saliency and image description. International Journal of Computer Vision, 45(2), 83–105. zbMATHCrossRefGoogle Scholar
  21. Leibe, B., Leonardis, A., & Schiele, B. (2004). Combined object categorization and segmentation with an implicit shape model. In ECCV workshop on statistical learning in computer vision. Google Scholar
  22. Li, Y., Shapiro, L., & Bilmes, J. (2005). A generative /discriminative learning algorithm for image classification. In ICCV (Vol. 2, pp. 1605–1612). Google Scholar
  23. Loeff, N., Arora, H., Sorokin, A., & Forsyth, D. (2005). Efficient unsupervised learning for localization and detection in object categories. In NIPS. Google Scholar
  24. Lowe, D. (2001). Local feature view clustering for 3D object recognition. In CVPR, (pp. 682–688). Google Scholar
  25. Mason, L., Baxter, J., Bartlett, P., & Frean, M. (2000). Boosting algorithms as gradient descent in function space. In NIPS (pp. 512–518). Google Scholar
  26. Murphy, K. P., Torralba, A., & Freeman, W. T. (2003). Using the forest to see the trees: a graphical model relating features, objects and scenes. In NIPS. Google Scholar
  27. NG, A. Y., & Jordan, M. I. (2001). On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes. In NIPS. Google Scholar
  28. Opelt, A., Fussenegger, M., Pinz, A., & Auer, P. (2004a). Object recognition with boosting (Technical report tr-emt-2004-01). Submitted to PAMI. Google Scholar
  29. Opelt, A., Fussenegger, M., Pinz, A., & Auer, P. (2004b). Weak hypotheses and boosting for generic object detection and recognition. In ECCV. Google Scholar
  30. Schapire, R. E., & Singer, Y. (1999). Improved boosting using confidence-rated predictions. Machine Learning, 37(3), 297–336. zbMATHCrossRefGoogle Scholar
  31. Serre, T., Wolf, L., & Poggio, T. (2005). A new biologically motivated framework for robust object recognition. In CVPR. Google Scholar
  32. Thureson, J., & Carlsson, S. (2004). Appearance based qualitative image description for object class recognition. In ECCV (pp. 518–529). Google Scholar
  33. Torralba, A., Murphy, K., & Freeman, W. T. (2004). Contextual models for object detection using boosted random fields. In NIPS. Google Scholar
  34. Ullman, S., Vidal-Naquet, M., & Sali, E. (2002). Visual features of intermediate complexity and their use in classification. Nature Neuroscience, 5, 682–687. Google Scholar
  35. Ulusoy, I., & Bishop, C. M. (2005). Generative versus discriminative methods for object recognition. In CVPR (Vol. 2, pp. 258–265). Google Scholar
  36. Vapnik, V. N. (1998). Statistical learning theory. New York: Wiley. zbMATHGoogle Scholar
  37. Vidal-Naquet, M., & Ullman, S. (2003). Object recognition with informative features and linear classification. In ICCV. Google Scholar
  38. Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In CVPR. Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  1. 1.Intel Research IsraelHaifaIsrael
  2. 2.Computer Science Department and the Center for Neural ComputationThe Hebrew University of JerusalemJerusalemIsrael

Personalised recommendations