Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/16587
Title: Projective dictionary pair learning for pattern classification
Authors: Gu, S
Zhang, L 
Zuo, W
Feng, X
Issue Date: 2014
Publisher: Neural information processing systems foundation
Source: Advances in neural information processing systems, 2014, v. 1, p. 793-801 How to cite?
Journal: Advances in Neural Information Processing Systems 
Abstract: Discriminative dictionary learning (DL) has been widely studied in various pattern classification problems. Most of the existing DL methods aim to learn a synthesis dictionary to represent the input signal while enforcing the representation coefficients and/or representation residual to be discriminative. However, the ?0 or ?1-norm sparsity constraint on the representation coefficients adopted in most DL methods makes the training and testing phases time consuming. We propose a new discriminative DL framework, namely projective dictionary pair learning (DPL), which learns a synthesis dictionary and an analysis dictionary jointly to achieve the goal of signal representation and discrimination. Compared with conventional DL methods, the proposed DPL method can not only greatly reduce the time complexity in the training and testing phases, but also lead to very competitive accuracies in a variety of visual classification tasks.
Description: 28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014, 8-13 December 2014
URI: http://hdl.handle.net/10397/16587
ISSN: 1049-5258
Appears in Collections:Conference Paper

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

61
Citations as of Sep 16, 2017

Page view(s)

76
Last Week
0
Last month
Checked on Sep 17, 2017

Google ScholarTM

Check



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.