The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.11 - November (2011 vol.33)
pp: 2302-2315
Evgeniy Bart , Palo Alto Research Center, Palo Alto
Max Welling , University of California Irvine, Irvine
Pietro Perona , California Institute of Technology, Pasadena
ABSTRACT
We introduce a nonparametric Bayesian model, called TAX, which can organize image collections into a tree-shaped taxonomy without supervision. The model is inspired by the Nested Chinese Restaurant Process (NCRP) and associates each image with a path through the taxonomy. Similar images share initial segments of their paths and thus share some aspects of their representation. Each internal node in the taxonomy represents information that is common to multiple images. We explore the properties of the taxonomy through experiments on a large (\sim 10^4) image collection with a number of users trying to locate quickly a given image. We find that the main benefits are easier navigation through image collections and reduced description length. A natural question is whether a taxonomy is the optimal form of organization for natural images. Our experiments indicate that although taxonomies can organize images in a useful manner, more elaborate structures may be even better suited for this task.
INDEX TERMS
Taxonomy, hierarchy, clustering.
CITATION
Evgeniy Bart, Max Welling, Pietro Perona, "Unsupervised Organization of Image Collections: Taxonomies and Beyond", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.33, no. 11, pp. 2302-2315, November 2011, doi:10.1109/TPAMI.2011.79
REFERENCES
[1] I. Biederman, "Visual Object Recognition," An Invitation to Cognitive Science, S.F. Kosslyn and D.N. Osherson, eds., second ed., vol. 2, pp. 121-165, MIT Press, 1995.
[2] L. Fei-Fei, R. Fergus, and P. Perona, "A Bayesian Approach to Unsupervised One-Shot Learning of Object Categories," Proc. IEEE Ninth Int'l Conf. Computer Vision, 2003.
[3] E. Bart and S. Ullman, "Cross-Generalization: Learning Novel Classes from a Single Example by Feature Replacement," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 2005.
[4] Y.W. Teh, M.I. Jordan, M.J. Beal, and D.M. Blei, "Hierarchical Dirichlet Processes," J. Am. Statistical Assoc., vol. 101, no. 476, pp. 1566-1581, 2006.
[5] Y. Amit, D. Geman, and X. Fan, "A Coarse-to-Fine Strategy for Multi-Class Shape Detection," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 12, pp. 1606-1621, Dec. 2004.
[6] G. Griffin and P. Perona, "Learning and Using Taxonomies for Fast Visual Categorization," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008.
[7] A. Zweig and D. Weinshall, "Exploiting Object Hierarchy: Combining Models from Different Category Levels," Proc. IEEE 11th Int'l Conf. Computer Vision, 2007.
[8] X. He and R. Zemel, "Latent Topic Random Fields: Learning Using a Taxonomy of Labels," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008.
[9] R. Duda, P. Hart, and D. Stork, Pattern Classification. John Wiley & Sons, 2001.
[10] M. Andreetto, L. Zelnik-Manor, and P. Perona, "Non-Parametric Probabilistic Image Segmentation," Proc. IEEE 11th Int'l Conf. Computer Vision, 2007.
[11] E.B. Sudderth, A. Torralba, W.T. Freeman, and A.S. Willsky, "Describing Visual Scenes Using Transformed Dirichlet Processes," Proc. Neural Information Processing Systems, 2005.
[12] E. Miller, N. Matsakis, and P. Viola, "Learning from One Example through Shared Densities on Transforms," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 464-471, 2000.
[13] A. Torralba, K.P. Murphy, and W.T. Freeman, "Sharing Features: Efficient Boosting Procedures for Multiclass Object Detection," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 2004.
[14] M. Fink, S. Shalev-Shwartz, Y. Singer, and S. Ullman, "Online Multiclass Learning by Interclass Hypothesis Sharing," Proc. 23rd Int'l Conf. Machine learning, 2006.
[15] K. Barnard, P. Duygulu, N. de Freitas, D. Forsyth, D. Blei, and M. Jordan, "Matching Words and Pictures," J. Machine Learning Research, vol. 3, pp. 1107-1135, 2003.
[16] D. Nister and H. Stewenius, "Scalable Recognition with a Vocabulary Tree," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 2006.
[17] D.M. Blei, T.L. Griffiths, M.I. Jordan, and J.B. Tenenbaum, "Hierarchical Topic Models and the Nested Chinese Restaurant Process," Proc. Neural Information Processing Systems, 2004.
[18] E. Bart, I. Porteous, P. Perona, and M. Welling, "Unsupervised Learning of Visual Taxonomies," Proc. IEEE Conf. Vision Pattern Recognition, 2008.
[19] J. Sivic, B.C. Russell, A. Zisserman, W.T. Freeman, and A.A. Efros, "Unsupervised Discovery of Visual Object Class Hierarchies," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008.
[20] L. Fei-Fei and P. Perona, "A Bayesian Hierarchical Model for Learning Natural Scene Categories," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 2005.
[21] D. Blei, A. Ng, and M. Jordan, "Latent Dirichlet Allocation," J. Machine Learning Research, vol. 3, pp. 993-1022, 2003.
[22] J. Sivic, B.C. Russell, A.A. Efros, A. Zisserman, and W.T. Freeman, "Discovering Objects and Their Localization in Images," Proc. IEEE 10th Int'l Conf. Computer Vision, pp. 370-377, 2005.
[23] M.D. Escobar and M. West, "Bayesian Density Estimation and Inference Using Mixtures," J. Am. Statistical Assoc., vol. 90, no. 430, pp. 577-588, 1995.
[24] D.G. Lowe, "Distinctive Image Features from Scale-invariant Keypoints," Int'l J. Computer Vision, vol. 60, no. 2, pp. 91-110, 2004.
[25] S. Lazebnik, C. Schmid, and J. Ponce, "Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 2006.
[26] P. Grunwald, "A Tutorial Introduction to the Minimum Description Length Principle," Advances in Minimum Description Length: Theory and Applications, 2005.
[27] E. Bart, "Speeding Up Gibbs Sampling by Variable Grouping," Proc. NIPS Workshop Applications for Topic Models: Text and Beyond, 2009.
21 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool