Bio-Inspired Structure Representation Based Cross-View Discriminative Subspace Learning via Simultaneous Local and Global Alignment
Recently, cross-view feature learning has been a hot topic in machine learning due to the wide applications of multiview data. Nevertheless, the distribution discrepancy between cross-views leads to the fact that instances of the different views from same class are farther than those within the same...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi-Wiley
2020-01-01
|
Series: | Complexity |
Online Access: | http://dx.doi.org/10.1155/2020/8872348 |
id |
doaj-9f96f601ba80476ab95357f102a68a87 |
---|---|
record_format |
Article |
spelling |
doaj-9f96f601ba80476ab95357f102a68a872020-11-25T04:09:57ZengHindawi-WileyComplexity1076-27871099-05262020-01-01202010.1155/2020/88723488872348Bio-Inspired Structure Representation Based Cross-View Discriminative Subspace Learning via Simultaneous Local and Global AlignmentAo Li0Yu Ding1Xunjiang Zheng2Deyun Chen3Guanglu Sun4Kezheng Lin5School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaOptical Navigation and Detection Division, Shanghai Aerospace Control Technology Institute, Shanghai 201109, ChinaSchool of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaRecently, cross-view feature learning has been a hot topic in machine learning due to the wide applications of multiview data. Nevertheless, the distribution discrepancy between cross-views leads to the fact that instances of the different views from same class are farther than those within the same view but from different classes. To address this problem, in this paper, we develop a novel cross-view discriminative feature subspace learning method inspired by layered visual perception from human. Firstly, the proposed method utilizes a separable low-rank self-representation model to disentangle the class and view structure layers, respectively. Secondly, a local alignment is constructed with two designed graphs to guide the subspace decomposition in a pairwise way. Finally, the global discriminative constraint on distribution center in each view is designed for further alignment improvement. Extensive cross-view classification experiments on several public datasets prove that our proposed method is more effective than other existing feature learning methods.http://dx.doi.org/10.1155/2020/8872348 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ao Li Yu Ding Xunjiang Zheng Deyun Chen Guanglu Sun Kezheng Lin |
spellingShingle |
Ao Li Yu Ding Xunjiang Zheng Deyun Chen Guanglu Sun Kezheng Lin Bio-Inspired Structure Representation Based Cross-View Discriminative Subspace Learning via Simultaneous Local and Global Alignment Complexity |
author_facet |
Ao Li Yu Ding Xunjiang Zheng Deyun Chen Guanglu Sun Kezheng Lin |
author_sort |
Ao Li |
title |
Bio-Inspired Structure Representation Based Cross-View Discriminative Subspace Learning via Simultaneous Local and Global Alignment |
title_short |
Bio-Inspired Structure Representation Based Cross-View Discriminative Subspace Learning via Simultaneous Local and Global Alignment |
title_full |
Bio-Inspired Structure Representation Based Cross-View Discriminative Subspace Learning via Simultaneous Local and Global Alignment |
title_fullStr |
Bio-Inspired Structure Representation Based Cross-View Discriminative Subspace Learning via Simultaneous Local and Global Alignment |
title_full_unstemmed |
Bio-Inspired Structure Representation Based Cross-View Discriminative Subspace Learning via Simultaneous Local and Global Alignment |
title_sort |
bio-inspired structure representation based cross-view discriminative subspace learning via simultaneous local and global alignment |
publisher |
Hindawi-Wiley |
series |
Complexity |
issn |
1076-2787 1099-0526 |
publishDate |
2020-01-01 |
description |
Recently, cross-view feature learning has been a hot topic in machine learning due to the wide applications of multiview data. Nevertheless, the distribution discrepancy between cross-views leads to the fact that instances of the different views from same class are farther than those within the same view but from different classes. To address this problem, in this paper, we develop a novel cross-view discriminative feature subspace learning method inspired by layered visual perception from human. Firstly, the proposed method utilizes a separable low-rank self-representation model to disentangle the class and view structure layers, respectively. Secondly, a local alignment is constructed with two designed graphs to guide the subspace decomposition in a pairwise way. Finally, the global discriminative constraint on distribution center in each view is designed for further alignment improvement. Extensive cross-view classification experiments on several public datasets prove that our proposed method is more effective than other existing feature learning methods. |
url |
http://dx.doi.org/10.1155/2020/8872348 |
work_keys_str_mv |
AT aoli bioinspiredstructurerepresentationbasedcrossviewdiscriminativesubspacelearningviasimultaneouslocalandglobalalignment AT yuding bioinspiredstructurerepresentationbasedcrossviewdiscriminativesubspacelearningviasimultaneouslocalandglobalalignment AT xunjiangzheng bioinspiredstructurerepresentationbasedcrossviewdiscriminativesubspacelearningviasimultaneouslocalandglobalalignment AT deyunchen bioinspiredstructurerepresentationbasedcrossviewdiscriminativesubspacelearningviasimultaneouslocalandglobalalignment AT guanglusun bioinspiredstructurerepresentationbasedcrossviewdiscriminativesubspacelearningviasimultaneouslocalandglobalalignment AT kezhenglin bioinspiredstructurerepresentationbasedcrossviewdiscriminativesubspacelearningviasimultaneouslocalandglobalalignment |
_version_ |
1715038292369473536 |