Boundary Detection Using F-Measure-, Filter- and Feature- (F3) Boost

  • Iasonas Kokkinos
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6312)


In this work we propose a boosting-based approach to boundary detection that advances the current state-of-the-art. To achieve this we introduce the following novel ideas: (a) we use a training criterion that approximates the F-measure of the classifier, instead of the exponential loss that is commonly used in boosting. We optimize this criterion using Anyboost. (b) We deal with the ambiguous information about orientation of the boundary in the annotation by treating it as a hidden variable, and train our classifier using Multiple-Instance Learning. (c) We adapt the Filterboost approach of [1] to leverage information from the whole training set to train our classifier, instead of using a fixed subset of points. (d) We extract discriminative features from appearance descriptors that are computed densely over the image. We demonstrate the performance of our approach on the Berkeley Segmentation Benchmark.


  1. 1.
    Bradley, J.K., Schapire, R.E.: Filterboost: Regression and classification on large datasets. In: NIPS (2007)Google Scholar
  2. 2.
    Marr, D.: Vision. W.H. Freeman, New York (1982)Google Scholar
  3. 3.
    Konishi, S., Yuille, A.L., Coughlan, J.M., Zhu, S.C.: Statistical Edge Detection: Learning and Evaluating Edge Cues. PAMI 25 (2003)Google Scholar
  4. 4.
    Martin, D., Fowlkes, C., Malik, J.: Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues. PAMI 26, 530–549 (2004)Google Scholar
  5. 5.
    Ren, X., Fowlkes, C., Malik, J.: Scale-invariant contour completion using crfs. In: ICCV (2005)Google Scholar
  6. 6.
    Dollar, P., Tu, Z., Belongie, S.: Supervised Learning of Edges and Object Boundaries. In: CVPR (2006)Google Scholar
  7. 7.
    Arbelaez, P.: Boundary Extraction in Natural Images Using Ultrametric Contour Maps. In: WPOCV (2006)Google Scholar
  8. 8.
    Maire, M., Arbelaez, P., Fowlkes, C., Malik., J.: Using Contours to Detect and Localize Junctions in Natural Images. In: CVPR (2008)Google Scholar
  9. 9.
    Ren, X.: Multiscale helps boundary detection. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 533–545. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  10. 10.
    Mairal, J., Leordeanu, M., Bach, F., Hebert, M., Ponce, J.: Discriminative sparse image models for class-specific edge detection and image interpretation. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 43–56. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  11. 11.
    Mason, L., Baxter, J., Bartlett, P., Frean, M.: Boosting algorithms as gradient descent. In: NIPS (2000)Google Scholar
  12. 12.
    Viola, P., Platt, J.C., Zhang, C.: Multiple Instance Boosting and Object Detection. In: NIPS (2006)Google Scholar
  13. 13.
    Tola, E., Lepetit, V., Fua, P.: A fast local descriptor for dense matching. In: CVPR (2008)Google Scholar
  14. 14.
    Canny, J.: A Computational Approach to Edge Detection. PAMI 8, 679–698 (1986)Google Scholar
  15. 15.
    Perona, P., Malik, J.: Detecting and Localizing Edges Composed of Steps, Peaks and Roofs. In: ICCV, pp. 52–57 (1990)Google Scholar
  16. 16.
    Catanzaro, B., Sundaram, N., Su, B., Lee, Y., Murphy, M., Keutzer, K.: Efficient high-quality image contour detection. In: ICCV (2009)Google Scholar
  17. 17.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik., J.: From contours to regions: An empirical evaluation. In: CVPR (2009)Google Scholar
  18. 18.
    Freund, Y., Schapire, R.: Experiments with a new Boosting Algorithm. In: ICML (1996)Google Scholar
  19. 19.
    Collins, M., Schapire, R.E., Singer, Y.: Logistic regression, adaboost and bregman distances. In: Machine Learning (2000)Google Scholar
  20. 20.
    Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting. Ann. Stat. (2000)Google Scholar
  21. 21.
    Joachims, T.: A support vector method for multivariate performance measures. In: ICML (2005)Google Scholar
  22. 22.
    Jansche, M.: Maximum expected f-measure training of logistic regression models. In: HLT 2005 (2005)Google Scholar
  23. 23.
    Friedman, J.H.: Stochastic gradient boosting. Comput. Stat. Data Anal. (2002)Google Scholar
  24. 24.
    Kokkinos, I.: Highly accurate boundary detection and grouping. In: CVPR (2010)Google Scholar
  25. 25.
    Ren, X., Fowlkes, C.C., Malik, J.: Figure/ground assignment in natural images. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 614–627. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  26. 26.
    Kokkinos, I., Yuille, A.: Scale Invariance without Scale Selection. In: CVPR (2008)Google Scholar
  27. 27.
    Cook, D., Lee, H.: Dimension reduction in binary response regression. JASA 94 (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Iasonas Kokkinos
    • 1
  1. 1.Department of Applied Mathematics, Ecole Centrale ParisINRIA-Saclay, GALEN Group 

Personalised recommendations