Abstract
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.
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
Tsochantaridis, I., Hofmann, T., Joachims, T., Altun, Y.: Support vector machine learning for interdependent and structured output spaces. In: ICML (2004)
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)
Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: ICML (2001)
Taskar, B., Guestrin, C., Koller, D.: Max-margin Markov networks. In: NIPS (2003)
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)
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)
Lucchi, A., Li, Y., Boix, X., Smith, K., Fua, P.: Are Spatial and Global Constraints Really Necessary for Segmentation? In: ICCV (2011)
Yu, C.N.J., Joachims, T.: Training structural svms with kernels using sampled cuts. In: KDD (2008)
Aliaksei, M., Severyn, A.: Fast support vector machines for structural kernels. In: ECML (2011)
Rahimi, A., Recht, B.: Random features for large-scale kernel machines. In: NIPS (2007)
Balcan, M.F., Blum, A., Vempala, S.: Kernels as features: On kernels, margins, and low-dimensional mappings. Mach. Learn. 65, 79–94 (2006)
Vedaldi, A., Zisserman, A.: Efficient additive kernels via explicit feature maps. In: PAMI (2011)
Maji, S., Berg, A.: Max-Margin Additive Classifiers for Detection. In: ICCV (2009)
Ladicky, L., Torr, P.: Locally Linear Support Vector Machines. In: ICML (2011)
Bertelli, L., Yu, T., Vu, D., Gokturk, B.: Kernelized Structural Svm Learning for Supervised Object Segmentation. In: CVPR (2011)
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)
Boykov, Y., Veksler, O., Zabih, R.: Fast Approximate Energy Minimization via Graph Cuts. PAMI 23 (2001)
Murphy, K.: Bayesian Map Learning in Dynamic Environments. In: NIPS, pp. 1015–1021 (1999)
Kolmogorov, V., Zabih, R.: What Energy Functions Can Be Minimized via Graph Cuts? PAMI 26, 147–159 (2004)
Finley, T., Joachims, T.: Training structural SVMs when exact inference is intractable. In: ICML (2008)
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)
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)
Shotton, J., Johnson, M., Cipolla, P.: Semantic Texton Forests for Image Categorization and Segmentation. In: CVPR (2008)
Ladicky, L., Russell, C., Kohli, P., Torr, P.H.S.: Associative Hierarchical CRFs for Object Class Image Segmentation. In: ICCV (2009)
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)
Felzenszwalb, P., Mcallester, D., Ramanan, D.: A Discriminatively Trained, Multiscale, Deformable Part Model. In: CVPR (2008)
Smith, K., Carleton, A., Lepetit, V.: Fast Ray Features for Learning Irregular Shapes. In: ICCV, pp. 397–404 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lucchi, A., Li, Y., Smith, K., Fua, P. (2012). Structured Image Segmentation Using Kernelized Features. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7573. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33709-3_29
Download citation
DOI: https://doi.org/10.1007/978-3-642-33709-3_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33708-6
Online ISBN: 978-3-642-33709-3
eBook Packages: Computer ScienceComputer Science (R0)