Abstract
In this paper we investigate a new method of learning part-based models for visual object recognition, from training data that only provides information about class membership (and not object location or configuration). This method learns both a model of local part appearance and a model of the spatial relations between those parts. In contrast, other work using such a weakly supervised learning paradigm has not considered the problem of simultaneously learning appearance and spatial models. Some of these methods use a “bag” model where only part appearance is considered whereas other methods learn spatial models but only given the output of a particular feature detector. Previous techniques for learning both part appearance and spatial relations have instead used a highly supervised learning process that provides substantial information about object part location. We show that our weakly supervised technique produces better results than these previous highly supervised methods. Moreover, we investigate the degree to which both richer spatial models and richer appearance models are helpful in improving recognition performance. Our results show that while both spatial and appearance information can be useful, the effect on performance depends substantially on the particular object class and on the difficulty of the test dataset.
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
Amit, Y., Trouve, A.: Pop: Patchwork of parts models for object recognition. Technical report, The University of Chicago (April 2005)
Crandall, D.J., Felzenszwalb, P.F., Huttenlocher, D.P.: Spatial priors for part-based recognition using statistical models. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 10–17 (2005)
Dance, C., Willamowski, J., Fan, L., Bray, C., Csurka, G.: Visual categorization with bags of keypoints. In: European Conference on Computer Vision (2004)
Dorko, G., Schmid, C.: Object class recognition using discriminative local features. Technical report, INRIA Grenoble (September 2005)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient matching of pictorial structures. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. II, pp. 66–73 (2000)
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: IEEE Conference on Computer Vision and Pattern Recognition (2003)
Fergus, R., Perona, P., Zisserman, A.: A sparse object category model for efficient learning and exhaustive recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 380–387 (2005)
Ioffe, S., Forsyth, D.A.: Probabilistic methods for finding people. International Journal of Computer Vision 43(1), 45–68 (2001)
Opelt, A., Fussenegger, M., Pinz, A., Auer, P.: Weak hypotheses and boosting for generic object detection and recognition. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3022, pp. 71–84. Springer, Heidelberg (2004)
Ullman, S., Sali, E., Vidal-Naquet, M.: A fragment-based approach to object representation and classification. In: Arcelli, C., Cordella, L.P., Sanniti di Baja, G. (eds.) IWVF 2001. LNCS, vol. 2059, p. 85. Springer, Heidelberg (2001)
Schneiderman, H., Kanade, T.: Probabilistic formulation for object recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (1998)
Serre, T., Wolf, L., Poggio, T.: A new biologically motivated framework for robust object recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2005)
Winn, J., Criminisi, A., Minka, T.: Object categorization by learned universal visual dictionary. In: IEEE International Conference on Computer Vision (2005)
Zhang, W., Yu, B., Samaras, D., Zelinsky, G.: Object class recognition using multiple layer boosting with heterogeneous features. In: IEEE Conference on Computer Vision and Pattern Recognition (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Crandall, D.J., Huttenlocher, D.P. (2006). Weakly Supervised Learning of Part-Based Spatial Models for Visual Object Recognition. In: Leonardis, A., Bischof, H., Pinz, A. (eds) Computer Vision – ECCV 2006. ECCV 2006. Lecture Notes in Computer Science, vol 3951. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11744023_2
Download citation
DOI: https://doi.org/10.1007/11744023_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-33832-1
Online ISBN: 978-3-540-33833-8
eBook Packages: Computer ScienceComputer Science (R0)