Exploiting Universum data in AdaBoost using gradient descent

Xu, J; Wu, Q; Zhang, J; Tang, Z

Exploiting Universum data in AdaBoost using gradient descent

Xu, J Wu, Q

Zhang, J

Tang, Z

Permalink

Publication Type:: Journal Article
Citation:: Image and Vision Computing, 2014, 32 (8), pp. 550 - 557
Issue Date:: 2014-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download full textAdobe PDF (626.6 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Xu, J	en_US
dc.contributor.author	Wu, Q https://orcid.org/0000-0001-5641-2483	en_US
dc.contributor.author	Zhang, J https://orcid.org/0000-0002-7240-3541	en_US
dc.contributor.author	Tang, Z	en_US
dc.date.issued	2014-01-01	en_US
dc.identifier.citation	Image and Vision Computing, 2014, 32 (8), pp. 550 - 557	en_US
dc.identifier.issn	0262-8856	en_US
dc.identifier.uri	http://hdl.handle.net/10453/34953
dc.description.abstract	Recently, Universum data that does not belong to any class of the training data, has been applied for training better classifiers. In this paper, we address a novel boosting algorithm called UAdaBoost that can improve the classification performance of AdaBoost with Universum data. UAdaBoost chooses a function by minimizing the loss for labeled data and Universum data. The cost function is minimized by a greedy, stagewise, functional gradient procedure. Each training stage of UAdaBoost is fast and efficient. The standard AdaBoost weights labeled samples during training iterations while UAdaBoost gives an explicit weighting scheme for Universum samples as well. In addition, this paper describes the practical conditions for the effectiveness of Universum learning. These conditions are based on the analysis of the distribution of ensemble predictions over training samples. Experiments on handwritten digits classification and gender classification problems are presented. As exhibited by our experimental results, the proposed method can obtain superior performances over the standard AdaBoost by selecting proper Universum data. © 2014 Elsevier B.V.	en_US
dc.relation.ispartof	Image and Vision Computing	en_US
dc.relation.isbasedon	10.1016/j.imavis.2014.04.009	en_US
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.title	Exploiting Universum data in AdaBoost using gradient descent	en_US
dc.type	Journal Article
utslib.citation.volume	8	en_US
utslib.citation.volume	32	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	0906 Electrical and Electronic Engineering	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
pubs.organisational-group	/University of Technology Sydney/Strength - GBDTC - Global Big Data Technologies
pubs.organisational-group	/University of Technology Sydney/Strength - INEXT - Innovation in IT Services and Applications
utslib.copyright.status	open_access
pubs.issue	8	en_US
pubs.publication-status	Published	en_US
pubs.volume	32	en_US

Abstract:

Recently, Universum data that does not belong to any class of the training data, has been applied for training better classifiers. In this paper, we address a novel boosting algorithm called UAdaBoost that can improve the classification performance of AdaBoost with Universum data. UAdaBoost chooses a function by minimizing the loss for labeled data and Universum data. The cost function is minimized by a greedy, stagewise, functional gradient procedure. Each training stage of UAdaBoost is fast and efficient. The standard AdaBoost weights labeled samples during training iterations while UAdaBoost gives an explicit weighting scheme for Universum samples as well. In addition, this paper describes the practical conditions for the effectiveness of Universum learning. These conditions are based on the analysis of the distribution of ensemble predictions over training samples. Experiments on handwritten digits classification and gender classification problems are presented. As exhibited by our experimental results, the proposed method can obtain superior performances over the standard AdaBoost by selecting proper Universum data. © 2014 Elsevier B.V.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/34953