Efficient Inference of Spatial Hierarchical Models

Jan Mačák, Ondřej Drbohlav

Abstract

The long term goal of artificial intelligence and computer vision is to be able to build models of the world automatically and to use them for interpretation of new situations. It is natural that such models are efficiently organized in a hierarchical manner; a model is build by sub-models, these sub-models are again build of another models, and so on. These building blocks are usually shareable; different objects may consist of the same components. In this paper, we describe a hierarchical probabilistic model for visual domain and propose a method for its efficient inference based on data partitioning and dynamic programming. We show the behaviour of the model, which is in this case made manually, and inference method on a controlled yet challenging dataset consisting of rotated, scaled and occluded letters. The experiments show that the proposed model is robust to all above-mentioned aspects.

References

  1. Bienenstock, E., Geman, S., and Potter, D. (1996). Compositionality, MDL priors, and object recognition. In Mozer, M., Jordan, M. I., and Petsche, T., editors, NIPS, pages 838-844. MIT Press.
  2. Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer Science+Bussiness Media, New York, NY.
  3. Felzenszwalb, P. and Huttenlocher, D. (2000). Efficient matching of pictorial structures. In Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on, volume 2, pages 66 -73 vol.2.
  4. Fidler, S., Berginc, G., and Leonardis, A. (2006). Hierarchical statistical learning of generic parts of object structure. In Proc. CVPR, pages 182-189.
  5. Fidler, S. and Leonardis, A. (2007). Towards scalable representations of object categories: Learning a hierarchy of parts. In Proc. CVPR.
  6. Karp, R. M. (1972). Reducibility among combinatorial problems. In Miller, R. E. and Thatcher, J. W., editors, Complexity of Computer Computations, The IBM Research Symposia Series, pages 85-103. Plenum Press, New York.
  7. Kokkinos, I. and Yuille, A. (2011). Inference and learning with hierarchical shape models. International Journal of Computer Vision, 93:201-225. 10.1007/s11263- 010-0398-7.
  8. Mooij, J. and Kappen, H. (2007). Sufficient conditions for convergence of the sum-product algorithm. Information Theory, IEEE Transactions on, 53(12):4422- 4437.
  9. Ommer, B. and Buhmann, J. (2010). Learning the compositional nature of visual object categories for recognition. IEEE Trans. Pattern Anal. Mach. Intell., 32(3):501 -516.
  10. Pearl, J. (1988). Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA.
  11. Tsotsos, J. K. (1990). Analyzing vision at the complexity level. Behavioral and Brain Sciences, 13(03):423- 445.
  12. Ullman, S. (2007). Object recognition and segmentation by a fragment-based hierarchy. Trends in Cognitive Sciences, 11(2):58 - 64.
  13. Weiss, Y. (2000). Correctness of Local Probability Propagation in Graphical Models with Loops. Neural Comp., 12(1):1-41.
  14. Zhu, L., Chen, Y., and Yuille, A. L. (2010). Learning a hierarchical deformable template for rapid deformable object parsing. IEEE Trans. Pattern Anal. Mach. Intell., 32(6):1029-1043.
  15. Zhu, L. L., Chen, Y., and Yuille, A. (2011). Recursive compositional models for vision: Description and review of recent work. J. Math. Imaging Vis., 41(1-2):122- 146.
  16. Zhu, S.-C. and Mumford, D. (2006). A stochastic grammar of images. Found. Trends. Comput. Graph. Vis., 2:259-362.
Download


Paper Citation


in Harvard Style

Mačák J. and Drbohlav O. (2014). Efficient Inference of Spatial Hierarchical Models . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-003-1, pages 500-506. DOI: 10.5220/0004687705000506


in Bibtex Style

@conference{visapp14,
author={Jan Mačák and Ondřej Drbohlav},
title={Efficient Inference of Spatial Hierarchical Models},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={500-506},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004687705000506},
isbn={978-989-758-003-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014)
TI - Efficient Inference of Spatial Hierarchical Models
SN - 978-989-758-003-1
AU - Mačák J.
AU - Drbohlav O.
PY - 2014
SP - 500
EP - 506
DO - 10.5220/0004687705000506