Abstract
A conceptually very simple unsupervised algorithm for learning structure in the form of a hierarchical probabilistic model is described in this paper. The proposed probabilistic model can easily work with any type of image primitives such as edge segments, non-max-suppressed filter set responses, texels, distinct image regions, SIFT features, etc., and is even capable of modelling non-rigid and/or visually variable objects. The model has recursive form and consists of sets of simple and gradually growing sub-models that are shared and learned individually in layers. The proposed probabilistic framework enables to exactly compute the probability of presence of a certain model, regardless on which layer it actually is. All these learned models constitute a rich set of independent structure elements of variable complexity that can be used as features in various recognition tasks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Training and classification of same object classes in different datasets.
- 2.
For the sake of clarity, the unnecessary indices are ommited.
- 3.
The grouping is actually generated randomly.
References
Tsotsos, J.K.: Analyzing vision at the complexity level. Behav. Brain Sci. 13, 423–445 (1990)
Bienenstock, E., Geman, S., Potter, D.: Compositionality, MDL priors, and object recognition. In: Mozer, M., Jordan, M.I., Petsche, T. (eds.) NIPS, pp. 838–844. MIT Press, Cambridge (1996)
Fukushima, K.: Neocognitron: a hierarchical neural network capable of visual pattern recognition. Neural Netw. 1, 119–130 (1988)
Serre, T., Wolf, L., Bileschi, S., Riesenhuber, M., Poggio, T.: Robust object recognition with cortex-like mechanisms. IEEE Trans. Pattern Anal. Mach. Intell. 29, 411–426 (2007)
Zhu, S.C., Mumford, D.: A stochastic grammar of images. Found. Trends. Comput. Graph. Vis. 2, 259–362 (2006)
Zhu, L., Chen, Y., Yuille, A.L.: Learning a hierarchical deformable template for rapid deformable object parsing. IEEE Trans. Pattern Anal. Mach. Intell. 32, 1029–1043 (2010)
Si, Z., Zhu, S.C.: Learning and-or templates for object recognition and detection. IEEE Trans. Pattern Anal. Mach. Intell. 35, 2189–2205 (2013)
Lee, H., Grosse, R., Ranganath, R., Ng, A.Y.: Unsupervised learning of hierarchical representations with convolutional deep belief networks. Commun. ACM 54, 95–103 (2011)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C., Bottou, L., Weinberger, K. (eds.) Advances in Neural Information Processing Systems 25, pp. 1097–1105. Curran Associates, Inc., Red Hook (2012)
Hinton, G.E., Osindero, S.: A fast learning algorithm for deep belief nets. Neural Comput. 18, 1527–1554 (2006)
Dai, J., Hong, Y., Hu, W., Zhu, S.C., Wu, Y.N.: Unsupervised learning of dictionaries of hierarchical compositional models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)
Grünwald, P.D.: The Minimum Description Length Principle. MIT Press, Cambridge (2007)
Fidler, S., Berginc, G., Leonardis, A.: Hierarchical statistical learning of generic parts of object structure. In: Proceedings of the IEEE conference of CVPR, pp. 182–189 (2006)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann Publishers Inc., San Francisco (1988)
Fidler, S., Leonardis, A.: Towards scalable representations of object categories: learning a hierarchy of parts. In: Proceedings of the IEEE conference of CVPR (2007)
Zhu, L(.L)., Lin, C., Huang, H., Chen, Y., Yuille, A.L.: Unsupervised structure learning: hierarchical recursive composition, suspicious coincidence and competitive exclusion. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 759–773. Springer, Heidelberg (2008)
Si, Z., Zhu, S.C.: Learning hybrid image templates (HIT) by information projection. IEEE Trans. Pattern Anal. Mach. Intell. 34, 1354–1367 (2012)
Acknowledgement
The authors were supported by the Czech Science Foundation under the Project P103/12/1578.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Mačák, J., Drbohlav, O. (2015). A Simple Stochastic Algorithm for Structural Features Learning. In: Jawahar, C., Shan, S. (eds) Computer Vision - ACCV 2014 Workshops. ACCV 2014. Lecture Notes in Computer Science(), vol 9010. Springer, Cham. https://doi.org/10.1007/978-3-319-16634-6_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-16634-6_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16633-9
Online ISBN: 978-3-319-16634-6
eBook Packages: Computer ScienceComputer Science (R0)