From a Set of Shapes to Object Discovery

  • Nadia Payet
  • Sinisa Todorovic
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6315)


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.


Dynamic Time Warping Object Discovery Graph Edge Negative Edge Image Contour 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

978-3-642-15555-0_5_MOESM1_ESM.pdf (152 kb)
Electronic Supplementary Material (153 KB)


  1. 1.
    Biederman, I.: Surface versus edge-based determinants of visual recognition. Cognitive Psychology 20, 38–64 (1988)CrossRefGoogle Scholar
  2. 2.
    Shotton, J., Blake, A., Cipolla, R.: Multiscale categorical object recognition using contour fragments. PAMI 30, 1270–1281 (2008)Google Scholar
  3. 3.
    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)CrossRefGoogle Scholar
  4. 4.
    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)CrossRefGoogle Scholar
  5. 5.
    Kokkinos, I., Yuille, A.L.: HOP: Hierarchical object parsing. In: CVPR (2009)Google Scholar
  6. 6.
    Bai, X., Wang, X., Liu, W., Latecki, L.J., Tu, Z.: Active skeleton for non-rigid object detection. In: ICCV (2009)Google Scholar
  7. 7.
    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)Google Scholar
  8. 8.
    Todorovic, S., Ahuja, N.: Unsupervised category modeling, recognition, and segmentation in images. IEEE TPAMI 30, 1–17 (2008)Google Scholar
  9. 9.
    Kim, G., Faloutsos, C., Hebert, M.: Unsupervised modeling of object categories using link analysis techniques. In: CVPR (2008)Google Scholar
  10. 10.
    Lee, Y.J., Grauman, K.: Shape discovery from unlabeled image collections. In: CVPR (2009)Google Scholar
  11. 11.
    Felzenszwalb, P., McAllester, D.: A min-cover approach for finding salient curves. In: CVPR POCV (2006)Google Scholar
  12. 12.
    Lin, L., Zeng, K., Liu, X., Zhu, S.C.: Layered graph matching by composite cluster sampling with collaborative and competitive interactions. In: CVPR (2009)Google Scholar
  13. 13.
    Barbu, A., Zhu, S.C.: Generalizing Swendsen-Wang to sampling arbitrary posterior probabilities. IEEE TPAMI 27, 1239–1253 (2005)Google Scholar
  14. 14.
    Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. PAMI 24, 509–522 (2002)Google Scholar
  15. 15.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)CrossRefGoogle Scholar
  16. 16.
    Chong, E.K.P., Zak, S.H.: An introduction to optimization. Wiley-Interscience, Hoboken (2001)zbMATHGoogle Scholar
  17. 17.
    Lee, Y.J., Grauman, K.: Foreground focus: Unsupervised learning from partially matching images. In: BMVC (2008)Google Scholar
  18. 18.
    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)Google Scholar
  19. 19.
    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)Google Scholar
  20. 20.
    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)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Nadia Payet
    • 1
  • Sinisa Todorovic
    • 1
  1. 1.Kelley Engineering CenterOregon State UniversityCorvallisUSA

Personalised recommendations