Structured Image Segmentation Using Kernelized Features

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7573)


Most state-of-the-art approaches to image segmentation formulate the problem using Conditional Random Fields. These models typically include a unary term and a pairwise term, whose parameters must be carefully chosen for optimal performance. Recently, structured learning approaches such as Structured SVMs (SSVM) have made it possible to jointly learn these model parameters. However, they have been limited to linear kernels, since more powerful non-linear kernels cause the learning to become prohibitively expensive. In this paper, we introduce an approach to “kernelize” the features so that a linear SSVM framework can leverage the power of non-linear kernels without incurring the high computational cost. We demonstrate the advantages of this approach in a series of image segmentation experiments on the MSRC data set as well as 2D and 3D datasets containing imagery of neural tissue acquired with electron microscopes.


Feature Vector Image Segmentation Unary Term Optimal Label Structural Kernel 
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.


  1. 1.
    Tsochantaridis, I., Hofmann, T., Joachims, T., Altun, Y.: Support vector machine learning for interdependent and structured output spaces. In: ICML (2004)Google Scholar
  2. 2.
    Shotton, J., Winn, J., Rother, C., Criminisi, A.: Textonboost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context. IJCV 81 (2009)Google Scholar
  3. 3.
    Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: ICML (2001)Google Scholar
  4. 4.
    Taskar, B., Guestrin, C., Koller, D.: Max-margin Markov networks. In: NIPS (2003)Google Scholar
  5. 5.
    Szummer, M., Kohli, P., Hoiem, D.: Learning CRFs Using Graph Cuts. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 582–595. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  6. 6.
    Nowozin, S., Gehler, P.V., Lampert, C.H.: On Parameter Learning in CRF-Based Approaches to Object Class Image Segmentation. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part VI. LNCS, vol. 6316, pp. 98–111. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  7. 7.
    Lucchi, A., Li, Y., Boix, X., Smith, K., Fua, P.: Are Spatial and Global Constraints Really Necessary for Segmentation? In: ICCV (2011)Google Scholar
  8. 8.
    Yu, C.N.J., Joachims, T.: Training structural svms with kernels using sampled cuts. In: KDD (2008)Google Scholar
  9. 9.
    Aliaksei, M., Severyn, A.: Fast support vector machines for structural kernels. In: ECML (2011)Google Scholar
  10. 10.
    Rahimi, A., Recht, B.: Random features for large-scale kernel machines. In: NIPS (2007)Google Scholar
  11. 11.
    Balcan, M.F., Blum, A., Vempala, S.: Kernels as features: On kernels, margins, and low-dimensional mappings. Mach. Learn. 65, 79–94 (2006)CrossRefGoogle Scholar
  12. 12.
    Vedaldi, A., Zisserman, A.: Efficient additive kernels via explicit feature maps. In: PAMI (2011)Google Scholar
  13. 13.
    Maji, S., Berg, A.: Max-Margin Additive Classifiers for Detection. In: ICCV (2009)Google Scholar
  14. 14.
    Ladicky, L., Torr, P.: Locally Linear Support Vector Machines. In: ICML (2011)Google Scholar
  15. 15.
    Bertelli, L., Yu, T., Vu, D., Gokturk, B.: Kernelized Structural Svm Learning for Supervised Object Segmentation. In: CVPR (2011)Google Scholar
  16. 16.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Suesstrunk, S.: SLIC Superpixels Compared to State-of-the-art Superpixel Methods. PAMI (in press, 2012)Google Scholar
  17. 17.
    Boykov, Y., Veksler, O., Zabih, R.: Fast Approximate Energy Minimization via Graph Cuts. PAMI 23 (2001)Google Scholar
  18. 18.
    Murphy, K.: Bayesian Map Learning in Dynamic Environments. In: NIPS, pp. 1015–1021 (1999)Google Scholar
  19. 19.
    Kolmogorov, V., Zabih, R.: What Energy Functions Can Be Minimized via Graph Cuts? PAMI 26, 147–159 (2004)CrossRefGoogle Scholar
  20. 20.
    Finley, T., Joachims, T.: Training structural SVMs when exact inference is intractable. In: ICML (2008)Google Scholar
  21. 21.
    Gonfaus, J., Boix, X., Weijer, J., Bagdanov, A., Serrat, J., Gonzalez, J.: Harmony Potentials for Joint Classification and Segmentation. In: CVPR, pp. 3280–3287 (2010)Google Scholar
  22. 22.
    van Gemert, J.C., Geusebroek, J.-M., Veenman, C.J., Smeulders, A.W.M.: Kernel Codebooks for Scene Categorization. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 696–709. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  23. 23.
    Shotton, J., Johnson, M., Cipolla, P.: Semantic Texton Forests for Image Categorization and Segmentation. In: CVPR (2008)Google Scholar
  24. 24.
    Ladicky, L., Russell, C., Kohli, P., Torr, P.H.S.: Associative Hierarchical CRFs for Object Class Image Segmentation. In: ICCV (2009)Google Scholar
  25. 25.
    Lucchi, A., Smith, K., Achanta, R., Knott, G., Fua, P.: Supervoxel-Based Segmentation of Mitochondria in Em Image Stacks with Learned Shape Features. TMI 31, 474–486 (2011)Google Scholar
  26. 26.
    Felzenszwalb, P., Mcallester, D., Ramanan, D.: A Discriminatively Trained, Multiscale, Deformable Part Model. In: CVPR (2008)Google Scholar
  27. 27.
    Smith, K., Carleton, A., Lepetit, V.: Fast Ray Features for Learning Irregular Shapes. In: ICCV, pp. 397–404 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.Computer Vision LaboratoryEPFLLausanneSwitzerland
  2. 2.Light Microscopy CenterETHZZurichSwitzerland

Personalised recommendations