Abstract
This paper presents an approach to object discovery in a given unlabeled image set, based on mining repetitive spatial configurations of image contours. Contours that similarly deform from one image to another are viewed as collaborating, or, otherwise, conflicting. This is captured by a graph over all pairs of matching contours, whose maximum a posteriori multicoloring assignment is taken to represent the shapes of discovered objects. Multicoloring is conducted by our new Coordinate Ascent Swendsen-Wang cut (CASW). CASW uses the Metropolis-Hastings (MH) reversible jumps to probabilistically sample graph edges, and color nodes. CASW extends SW cut by introducing a regularization in the posterior of multicoloring assignments that prevents the MH jumps to arrive at trivial solutions. Also, CASW seeks to learn parameters of the posterior via maximizing a lower bound of the MH acceptance rate. This speeds up multicoloring iterations, and facilitates MH jumps from local minima. On benchmark datasets, we outperform all existing approaches to unsupervised object discovery.
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
Biederman, I.: Surface versus edge-based determinants of visual recognition. Cognitive Psychology 20, 38–64 (1988)
Shotton, J., Blake, A., Cipolla, R.: Multiscale categorical object recognition using contour fragments. PAMI 30, 1270–1281 (2008)
Ferrari, V., Tuytelaars, T., Gool, L.V.: Object detection by contour segment networks. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3953, pp. 14–28. Springer, Heidelberg (2006)
Zhu, Q., Wang, L., Wu, Y., Shi, J.: Contour context selection for object detection: A set-to-set contour matching approach. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 774–787. Springer, Heidelberg (2008)
Kokkinos, I., Yuille, A.L.: HOP: Hierarchical object parsing. In: CVPR (2009)
Bai, X., Wang, X., Liu, W., Latecki, L.J., Tu, Z.: Active skeleton for non-rigid object detection. In: ICCV (2009)
Russell, B., Freeman, W., Efros, A., Sivic, J., Zisserman, A.: Using multiple segmentations to discover objects and their extent in image collections. In: CVPR (2006)
Todorovic, S., Ahuja, N.: Unsupervised category modeling, recognition, and segmentation in images. IEEE TPAMI 30, 1–17 (2008)
Kim, G., Faloutsos, C., Hebert, M.: Unsupervised modeling of object categories using link analysis techniques. In: CVPR (2008)
Lee, Y.J., Grauman, K.: Shape discovery from unlabeled image collections. In: CVPR (2009)
Felzenszwalb, P., McAllester, D.: A min-cover approach for finding salient curves. In: CVPR POCV (2006)
Lin, L., Zeng, K., Liu, X., Zhu, S.C.: Layered graph matching by composite cluster sampling with collaborative and competitive interactions. In: CVPR (2009)
Barbu, A., Zhu, S.C.: Generalizing Swendsen-Wang to sampling arbitrary posterior probabilities. IEEE TPAMI 27, 1239–1253 (2005)
Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. PAMI 24, 509–522 (2002)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)
Chong, E.K.P., Zak, S.H.: An introduction to optimization. Wiley-Interscience, Hoboken (2001)
Lee, Y.J., Grauman, K.: Foreground focus: Unsupervised learning from partially matching images. In: BMVC (2008)
Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. In: CVPR (2004)
Russell, B.C., Torralba, A., Murphy, K.P., Freeman, W.T.: Labelme: a database and web-based tool for image annotation. Technical Report AIM-2005-025, MIT (2005)
Borenstein, E., Ullman, S.: Class-specific, top-down segmentation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part II. LNCS, vol. 2351, pp. 109–122. Springer, Heidelberg (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
1 Electronic Supplementary Material
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Payet, N., Todorovic, S. (2010). From a Set of Shapes to Object Discovery. In: Daniilidis, K., Maragos, P., Paragios, N. (eds) Computer Vision – ECCV 2010. ECCV 2010. Lecture Notes in Computer Science, vol 6315. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15555-0_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-15555-0_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15554-3
Online ISBN: 978-3-642-15555-0
eBook Packages: Computer ScienceComputer Science (R0)