Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/20671
Title: Multi-instance multi-label image classification : a neural approach
Authors: Chen, Z
Chi, Z 
Fu, H
Feng, D
Keywords: Image classification
Multi-instance multi-label learning
Neural networks
Synthetic data
Issue Date: 2013
Publisher: Elsevier
Source: Neurocomputing, 2013, v. 99, p. 298-306 How to cite?
Journal: Neurocomputing 
Abstract: In this paper, a multi-instance multi-label algorithm based on neural networks is proposed for image classification. The proposed algorithm, termed multi-instance multi-label neural network (MIMLNN), consists of two stages of MultiLayer Perceptrons (MLP). For multi-instance multi-label image classification, all the regional features are fed to the first-stage MLP, with one MLP copy processing one image region. After that, the MLP in the second stage incorporates the outputs of the first-stage MLPs to produce the final labels for the input image. The first-stage MLP is expected to model the relationship between regions and labels, while the second-stage MLP aims at capturing the label correlation for classification refinement. Error Back-Propagation (BP) approach is adopted to tune the parameters of MIMLNN. In view of that traditional gradient descent algorithm suffers from long-term dependency problem, a refined BP algorithm named Rprop is extended to effectively train MIMLNN. The experiments are conducted on a synthetic dataset and the Corel dataset. Experimental results demonstrate the superior performance of MIMLNN comparing with state-of-the-art algorithms for multi-instance multi-label image classification.
URI: http://hdl.handle.net/10397/20671
ISSN: 0925-2312
EISSN: 1872-8286
DOI: 10.1016/j.neucom.2012.08.001
Appears in Collections:Journal/Magazine Article

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

SCOPUSTM   
Citations

12
Last Week
0
Last month
0
Citations as of Aug 15, 2017

WEB OF SCIENCETM
Citations

5
Last Week
0
Last month
0
Citations as of Aug 20, 2017

Page view(s)

38
Last Week
1
Last month
Checked on Aug 20, 2017

Google ScholarTM

Check

Altmetric



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