Contractive Rectifier Networks for Nonlinear Maximum Margin Classification
Senjian An, Munawar Hayat, Salman H. Khan, Mohammed Bennamoun, Farid Boussaid, Ferdous Sohel
Abstract
To find the optimal nonlinear separating boundary with maximum margin in the input data space, this paper proposes Contractive Rectifier Networks (CRNs), wherein the hidden-layer transformations are restricted to be contraction mappings. The contractive constraints ensure that the achieved separating margin in the input space is larger than or equal to the separating margin in the output layer. The training of the proposed CRNs is formulated as a linear support vector machine (SVM) in the output layer, combined with two or more contractive hidden layers. Effective algorithms have been proposed to address the optimization challenges arising from contraction constraints. Experimental results on MNIST, CIFAR-10, CIFAR-100 and MIT-67 datasets demonstrate that the proposed contractive rectifier networks consistently outperform their conventional unconstrained rectifier network counterparts.
BibTeX
@inproceedings{iccv2015_contractiverecti,
title = {Contractive Rectifier Networks for Nonlinear Maximum Margin Classification},
author = {Senjian An and Munawar Hayat and Salman H. Khan and Mohammed Bennamoun and Farid Boussaid and Ferdous Sohel},
booktitle = {ICCV 2015},
year = {2015}
}