Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/107656
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: The use of deep learning features in a hierarchical classifier learned with the minimization of a non-greedy loss function that delays gratification
Author: Liao, Z.
Carneiro, G.
Citation: Proceedings of the 2015 IEEE International Conference on Image Processing, 2015 / vol.2015-December, pp.4540-4544
Publisher: IEEE
Issue Date: 2015
Series/Report no.: IEEE International Conference on Image Processing ICIP
ISBN: 9781479983391
ISSN: 1522-4880
Conference Name: IEEE International Conference on Image Processing (ICIP) (27 Sep 2015 - 30 Sep 2015 : Quebec City, CANADA)
Statement of
Responsibility: 
Zhibin Liao and Gustavo Carneiro
Abstract: Recently, we have observed the traditional feature representations are being rapidly replaced by the deep learning representations, which produce significantly more accurate classification results when used together with the linear classifiers. However, it is widely known that non-linear classifiers can generally provide more accurate classification but at a higher computational cost involved in their training and testing procedures. In this paper, we propose a new efficient and accurate non-linear hierarchical classification method that uses the aforementioned deep learning representations. In essence, our classifier is based on a binary tree, where each node is represented by a linear classifier trained using a loss function that minimizes the classification error in a non-greedy way, in addition to postponing hard classification problems to further down the tree. In comparison with linear classifiers, our training process increases only marginally the training and testing time complexities, while showing competitive classification accuracy results. In addition, our method is shown to generalize better than shallow non-linear classifiers. Empirical validation shows that the proposed classifier produces more accurate classification results when compared to several linear and non-linear classifiers on Pascal VOC07 database.
Keywords: Training, support vector machines, testing, binary trees, boosting, complexity theory
Rights: © 2015 IEEE
RMID: 0030043412
DOI: 10.1109/ICIP.2015.7351666
Grant ID: http://purl.org/au-research/grants/arc/CE140100016
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_107656.pdfRestricted Access3.39 MBAdobe PDFView/Open


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