Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/62108
Title: Field effect deep networks for image recognition with incomplete data
Authors: Zhong, SH
Liu, Y 
Hu, KA
Keywords: Deep learning
Image recognition
Incomplete data
Missing features
Issue Date: 2016
Publisher: Association for Computing Machinery
Source: ACM transactions on multimedia computing communications and applications, 2016, v. 12, no. 4, 52 How to cite?
Journal: ACM transactions on multimedia computing communications and applications 
Abstract: Image recognition with incomplete data is a well-known hard problem in computer vision and machine learning. This article proposes a novel deep learning technique called Field Effect Bilinear Deep Networks (FEBDN) for this problem. To address the difficulties of recognizing incomplete data, we design a novel second-order deep architecture with the Field Effect Restricted Boltzmann Machine, which models the reliability of the delivered information according to the availability of the features. Based on this new architecture, we propose a new three-stage learning procedure with field effect bilinear initialization, field effect abstraction and estimation, and global fine-tuning with missing features adjustment. By integrating the reliability of features into the new learning procedure, the proposed FEBDN can jointly determine the classification boundary and estimate the missing features. FEBDN has demonstrated impressive performance on recognition and estimation tasks in various standard datasets.
URI: http://hdl.handle.net/10397/62108
ISSN: 1551-6857 (print)
1551-6865 (online)
DOI: 10.1145/2957754
Appears in Collections:Journal/Magazine Article

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

SCOPUSTM   
Citations

2
Last Week
0
Last month
Citations as of Jan 7, 2018

WEB OF SCIENCETM
Citations

1
Last Week
0
Last month
Citations as of Jan 21, 2018

Page view(s)

58
Last Week
1
Last month
Citations as of Jan 8, 2018

Google ScholarTM

Check

Altmetric


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