Abstract
Learning from unlabeled images that contain various objects that change in pose, scale, and degree of occlusion is a challenging task in computer vision. Shared structures embody the consistence and coherence of features that repeatedly cooccur at an object class. They can be used as discriminative information to separate the various objects contained in unlabeled images. In this paper, we propose a maximum likelihood algorithm for unsupervised shared structure learning, where shared structures are represented as the strongly connected clusters of consistent pairwise relationships and shared structures of different order are learned through exploring and combining consistent pairwise spatial relationships. Two routines of sampling data, namely densely sampling and sparsely sampling, are also discussed in our work. We test our algorithm on a diverse set of data to verify its merits.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: IEEE Conference on CVPR (2003)
Heisele, B., Ho, P., Wu, J., Poggio, T.: Face recognition: component-based versus global approaches. Comput. Vis. Image Underst. 91(1–2), 6–21 (2003)
Loeff, N., Arora, H., Sorokin, A., Forsyth, D.A.: Efficient unsupervised learning for localization and detection in object categories. In: International Conference on NIPS (2005)
Parikh, D., Zitnick, C.L., Chen, T.: Unsupervised learning of hierarchical spatial structures. In: IEEE Conference on CVPR (2009)
Sivic, J., Zisserman, A.: Video data mining using configuration of viewpoint invariant regions. In: IEEE Conference on CVPR, pp. 488–495 (2004)
Froimovich, G., Rivlin, E., Shimshoni, I., Soldea, O.: Efficient search and verification for function based classification from real range images. Comput. Vis. Image Underst. 105(3), 200–217 (2007)
Pechuk, M., Soldea, O., Rivlin, E.: Learning function based classification from 3D imagery. Comput. Vis. Image Underst. 110(2), 173–191 (2008)
Weber, M.: Unsupervised learning of models for object recognition. Ph.D. thesis, California Institute of Technology, Pasadena, CA (2000)
Hoiem, D., Efros, A., Hebert, M.: Putting objects in perspective. In: IEEE Conference on CVPR (2006)
Rabinovich, A., Vedaldi, A., Galleguillos, C., Wiewiora, E., Belongie, S.: Objects in context. In: International Conference on ICCV (2007)
Leordeanu, M., Collins, R.: Unsupervised learning of object features from video sequences. In: IEEE Conference on CVPR (2005)
Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. 24(5), 603–619 (2002)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Conference on CVPR (2005)
Weber, M., Welling, M., Perona, P.: Unsupervised learning of models for recognition. In: International Conference on ECCV, pp. 18–32 (2000)
Agarwal, S., Roth, D.: Learning a sparse representation for object detection. In: International Conference on ECCV, pp. 113–130 (2002)
Green, K., Eggert, D., Stark, L., Bowyer, K.: Generic recognition of articulated objects through reasoning about potential function. Comput. Vis. Image Underst. 62(2), 177–193 (1995)
Perrotton, X., Sturzel, M., Roux, M.: Mining families of features for efficient object detection. In: IEEE Conference on ICIP (2010)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yang, F., Li, B. Unsupervised learning of spatial structures shared among images. Vis Comput 28, 175–180 (2012). https://doi.org/10.1007/s00371-011-0616-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-011-0616-5