Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/23574
Title: Bilinear deep learning for image classification
Authors: Zhong, SH
Liu, Y 
Liu, Y
Keywords: Bilinear discriminant projection
Deep learning
Image classification
Issue Date: 2011
Source: MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops, 2011, p. 343-352 How to cite?
Abstract: Image classification is a well-known classical problem in multimedia content analysis. This paper proposes a novel deep learning model called bilinear deep belief network (BDBN) for image classification. Unlike previous image classification models, BDBN aims to provide human-like judgment by referencing the architecture of the human visual system and the procedure of intelligent perception. Therefore, the multi-layer structure of the cortex and the propagation of information in the visual areas of the brain are realized faithfully. Unlike most existing deep models, BDBN utilizes a bilinear discriminant strategy to simulate the "initial guess" in human object recognition, and at the same time to avoid falling into a bad local optimum. To preserve the natural tensor structure of the image data, a novel deep architecture with greedy layer-wise reconstruction and global fine-tuning is proposed. To adapt real-world image classification tasks, we develop BDBN under a semi-supervised learning framework, which makes the deep model work well when labeled images are insufficient. Comparative experiments on three standard datasets show that the proposed algorithm outperforms both representative classification models and existing deep learning techniques. More interestingly, our demonstrations show that the proposed BDBN works consistently with the visual perception of humans.
Description: 19th ACM International Conference on Multimedia ACM Multimedia 2011, MM'11, Scottsdale, AZ, 28-1 December 2011
URI: http://hdl.handle.net/10397/23574
ISBN: 9781450306164
DOI: 10.1145/2072298.2072344
Appears in Collections:Conference Paper

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

SCOPUSTM   
Citations

37
Last Week
0
Last month
3
Citations as of Sep 10, 2017

Page view(s)

58
Last Week
3
Last month
Checked on Sep 24, 2017

Google ScholarTM

Check

Altmetric



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