UM  > 科技學院  > 機電工程系
Canonical Correlation Analysis Regularization: An Effective Deep Multi-View Learning Baseline for RGB-D Object Recognition
Lulu Tang1; Zhi-Xin Yang1; Kui Jia2
2019-03
Source PublicationIEEE Transactions on Cognitive and Developmental Systems
ISSN2379-8920
Volume11Issue:1Pages:107 - 118
Abstract

Object recognition methods based on multimodal data, color plus depth (RGB-D), usually treat each modality separately in feature extraction, which neglects implicit relations between two views and preserves noise from any view to the final representation. To address these limitations, we propose a novel canonical correlation analysis (CCA)-based multiview convolutional neural network (CNNs) framework for RGB-D object representation. The RGB and depth streams process corresponding images, respectively, then are connected by CCA module leading to a common-correlated feature space. In addition, to embed CCA into deep CNNs in a supervised manner, two different schemes are explored. One considers CCA as a regularization (CCAR) term adding to the loss function. However, solving CCA optimization directly is neither computationally efficient nor compatible with the mini-batch-based stochastic optimization. Thus, we further propose an approximation method of CCAR, using the obtained CCA projection matrices to replace the weights of feature concatenation layer at regular intervals. Such a scheme enjoys benefits of full CCAR and is efficient by amortizing its cost over many training iterations. Experiments on benchmark RGB-D object recognition datasets have shown that the proposed methods outperform most existing methods using the very same of their network architectures.

DOIhttps://www.doi.org/10.1109/TCDS.2018.2866587
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Robotics ; Neurosciences & Neurology
WOS SubjectComputer Science, Artificial Intelligence ; Robotics ; Neurosciences
WOS IDWOS:000461254800010
Fulltext Access
Citation statistics
Cited Times [WOS]:2   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionDEPARTMENT OF ELECTROMECHANICAL ENGINEERING
Corresponding AuthorZhi-Xin Yang; Kui Jia
Affiliation1.Department of Electromechanical Engineering, Faculty of Science and Technology, University of Macau, Macau, China
2.School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China
First Author AffilicationFaculty of Science and Technology
Corresponding Author AffilicationFaculty of Science and Technology
Recommended Citation
GB/T 7714
Lulu Tang,Zhi-Xin Yang,Kui Jia. Canonical Correlation Analysis Regularization: An Effective Deep Multi-View Learning Baseline for RGB-D Object Recognition[J]. IEEE Transactions on Cognitive and Developmental Systems,2019,11(1):107 - 118.
APA Lulu Tang,Zhi-Xin Yang,&Kui Jia.(2019).Canonical Correlation Analysis Regularization: An Effective Deep Multi-View Learning Baseline for RGB-D Object Recognition.IEEE Transactions on Cognitive and Developmental Systems,11(1),107 - 118.
MLA Lulu Tang,et al."Canonical Correlation Analysis Regularization: An Effective Deep Multi-View Learning Baseline for RGB-D Object Recognition".IEEE Transactions on Cognitive and Developmental Systems 11.1(2019):107 - 118.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Lulu Tang]'s Articles
[Zhi-Xin Yang]'s Articles
[Kui Jia]'s Articles
Baidu academic
Similar articles in Baidu academic
[Lulu Tang]'s Articles
[Zhi-Xin Yang]'s Articles
[Kui Jia]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Lulu Tang]'s Articles
[Zhi-Xin Yang]'s Articles
[Kui Jia]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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