Approximated Slack Scaling for Structural Support Vector Machines in Scene Depth Analysis
Joint Authors
Liu, Sheng
Zhai, Binbin
Chan, Sixian
Li, Feng
Zhan, Ye
Source
Mathematical Problems in Engineering
Issue
Vol. 2013, Issue 2013 (31 Dec. 2013), pp.1-11, 11 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2013-04-23
Country of Publication
Egypt
No. of Pages
11
Main Subjects
Abstract EN
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.
American Psychological Association (APA)
Liu, Sheng& Zhai, Binbin& Chan, Sixian& Li, Feng& Zhan, Ye. 2013. Approximated Slack Scaling for Structural Support Vector Machines in Scene Depth Analysis. Mathematical Problems in Engineering،Vol. 2013, no. 2013, pp.1-11.
https://search.emarefa.net/detail/BIM-1032182
Modern Language Association (MLA)
Liu, Sheng…[et al.]. Approximated Slack Scaling for Structural Support Vector Machines in Scene Depth Analysis. Mathematical Problems in Engineering No. 2013 (2013), pp.1-11.
https://search.emarefa.net/detail/BIM-1032182
American Medical Association (AMA)
Liu, Sheng& Zhai, Binbin& Chan, Sixian& Li, Feng& Zhan, Ye. Approximated Slack Scaling for Structural Support Vector Machines in Scene Depth Analysis. Mathematical Problems in Engineering. 2013. Vol. 2013, no. 2013, pp.1-11.
https://search.emarefa.net/detail/BIM-1032182
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1032182