Approximated Slack Scaling for Structural Support Vector Machines in Scene Depth Analysis

Based upon the framework of the structural support vector machines, this paper proposes two approaches to the depth restoration towards different scenes, that is, margin rescaling and the slack rescaling. The results show that both approaches achieve high convergence, while the slack approach yields better performance in prediction accuracy. However, due to its nondecomposability nature, the application of the slack approach is limited. This paper therefore introduces a novel approximation slack method to solve this problem, in which we propose a modified way of defining the loss functions to ensure the decomposability of the object function. During the training process, a bundle method is used to improve the computing efficiency. The results on Middlebury datasets show that proposed depth inference method solves the nondecomposability of slack scaling method and achieves relative acceptable accuracy. Our approximation approach can be an alternative for the slack scaling method to ensure efficient computation.

[1]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

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

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

[4]  Ben Taskar,et al.  Learning associative Markov networks , 2004, ICML.

[5]  Hai Tao,et al.  A method for learning matching errors for stereo computation , 2004, BMVC.

[6]  Shengyong Chen,et al.  Neural Network Based 3D Model Reconstruction with Highly Distorted Stereoscopic Sensors , 2005, IWANN.

[7]  Ben Taskar,et al.  Discriminative learning of Markov random fields for segmentation of 3D scan data , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[8]  Li Zhang,et al.  Parameter estimation for MRF stereo , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[9]  Thomas Hofmann,et al.  Large Margin Methods for Structured and Interdependent Output Variables , 2005, J. Mach. Learn. Res..

[10]  Ying Xu,et al.  The Probability Distribution for a Random Match between an Experimental-theoretical Spectral Pair in Tandem Mass Spectrometry , 2005, J. Bioinform. Comput. Biol..

[11]  Alexander J. Smola,et al.  Learning high-order MRF priors of color images , 2006, ICML.

[12]  Daniel P. Huttenlocher,et al.  Learning for stereo vision using the structured support vector machine , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Vladimir Pavlovic,et al.  Dimensionality reduction using covariance operator inverse regression , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Christoph H. Lampert,et al.  Learning to Localize Objects with Structured Output Regression , 2008, ECCV.

[15]  Rahul Gupta,et al.  Accurate max-margin training for structured output spaces , 2008, ICML '08.

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

[17]  Tsuhan Chen,et al.  Learning class-specific affinities for image labelling , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Cristian Sminchisescu,et al.  Structural SVM for visual localization and continuous state estimation , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[19]  Liefeng Bo,et al.  Structured output-associative regression , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Peter Carr,et al.  Minimizing energy functions on 4-connected lattices using elimination , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[21]  Shengyong Chen,et al.  Acceleration Strategies in Generalized Belief Propagation , 2012, IEEE Transactions on Industrial Informatics.