Contractive Rectifier Networks for nonlinear maximum margin classification

Senjian An, Munawar Hayat, Salman H. Khan, Mohammed Bennamoun, Farid Boussaid, Ferdous Sohel

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

5 Citations (Scopus)


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.

Original languageEnglish
Title of host publicationProceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015
EditorsKatsushi Ikeuchi, Christoph Schnörr, Josef Sivic, René Vidal
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages9
ISBN (Electronic)9781467383912
ISBN (Print)9781467383905
Publication statusPublished - 2015
Externally publishedYes
EventIEEE International Conference on Computer Vision 2015 - Santiago, Chile
Duration: 7 Dec 201513 Dec 2015
Conference number: 15th (Proceedings)


ConferenceIEEE International Conference on Computer Vision 2015
Abbreviated titleICCV 2015
Internet address

Cite this