Structured Image Segmentation Using Kernelized Features

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.

[1]  Pushmeet Kohli,et al.  Associative hierarchical CRFs for object class image segmentation , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[2]  Sebastian Nowozin,et al.  On Parameter Learning in CRF-Based Approaches to Object Class Image Segmentation , 2010, ECCV.

[3]  Kevin P. Murphy,et al.  Bayesian Map Learning in Dynamic Environments , 1999, NIPS.

[4]  Roberto Cipolla,et al.  Semantic texton forests for image categorization and segmentation , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Santosh S. Vempala,et al.  Kernels as features: On kernels, margins, and low-dimensional mappings , 2006, Machine Learning.

[6]  Olga Veksler,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Ben Taskar,et al.  Max-Margin Markov Networks , 2003, NIPS.

[8]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[9]  Thorsten Joachims,et al.  Training structural svms with kernels using sampled cuts , 2008, KDD.

[10]  Pascal Fua,et al.  Supervoxel-Based Segmentation of Mitochondria in EM Image Stacks With Learned Shape Features , 2012, IEEE Transactions on Medical Imaging.

[11]  Andrew Zisserman,et al.  Efficient Additive Kernels via Explicit Feature Maps , 2012, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Thomas Hofmann,et al.  Support vector machine learning for interdependent and structured output spaces , 2004, ICML.

[13]  Andrew J. Davison,et al.  Active Matching , 2008, ECCV.

[14]  Thorsten Joachims,et al.  Training structural SVMs when exact inference is intractable , 2008, ICML '08.

[15]  Alessandro Moschitti,et al.  Fast Support Vector Machines for Structural Kernels , 2011, ECML/PKDD.

[16]  Vladimir Kolmogorov,et al.  What energy functions can be minimized via graph cuts? , 2002, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Thomas Deselaers,et al.  ClassCut for Unsupervised Class Segmentation , 2010, ECCV.

[18]  Joost van de Weijer,et al.  Harmony potentials for joint classification and segmentation , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  Antonio Criminisi,et al.  TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context , 2007, International Journal of Computer Vision.

[20]  Philip H. S. Torr,et al.  Locally Linear Support Vector Machines , 2011, ICML.

[21]  Tianli Yu,et al.  Kernelized structural SVM learning for supervised object segmentation , 2011, CVPR 2011.

[22]  Benjamin Recht,et al.  Random Features for Large-Scale Kernel Machines , 2007, NIPS.

[23]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Derek Hoiem,et al.  Learning CRFs Using Graph Cuts , 2008, ECCV.

[25]  David A. McAllester,et al.  A discriminatively trained, multiscale, deformable part model , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[26]  Vincent Lepetit,et al.  Fast Ray features for learning irregular shapes , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[27]  Pascal Fua,et al.  Are spatial and global constraints really necessary for segmentation? , 2011, 2011 International Conference on Computer Vision.

[28]  Cor J. Veenman,et al.  Kernel Codebooks for Scene Categorization , 2008, ECCV.

[29]  Subhransu Maji,et al.  Max-margin additive classifiers for detection , 2009, 2009 IEEE 12th International Conference on Computer Vision.