The use of deep learning features in a hierarchical classifier learned with the minimization of a non-greedy loss function that delays gratification

Simple item page
dc.contributor.authorLiao, Z.
dc.contributor.authorCarneiro, G.
dc.contributor.conferenceIEEE International Conference on Image Processing (ICIP) (27 Sep 2015 - 30 Sep 2015 : Quebec City, CANADA)
dc.date.issued2015
dc.description.abstractRecently, 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.
dc.description.statementofresponsibilityZhibin Liao and Gustavo Carneiro
dc.identifier.citationProceedings / ICIP ... International Conference on Image Processing, 2015, vol.2015-December, pp.4540-4544
dc.identifier.doi10.1109/ICIP.2015.7351666
dc.identifier.isbn9781479983391
dc.identifier.issn1522-4880
dc.identifier.orcidLiao, Z. [0000-0001-9965-4511]
dc.identifier.orcidCarneiro, G. [0000-0002-5571-6220]
dc.identifier.urihttp://hdl.handle.net/2440/107656
dc.language.isoen
dc.publisherIEEE
dc.relation.granthttp://purl.org/au-research/grants/arc/CE140100016
dc.relation.ispartofseriesIEEE International Conference on Image Processing ICIP
dc.rights© 2015 IEEE
dc.source.urihttps://doi.org/10.1109/icip.2015.7351666
dc.subjectTraining, support vector machines, testing, binary trees, boosting, complexity theory
dc.titleThe use of deep learning features in a hierarchical classifier learned with the minimization of a non-greedy loss function that delays gratification
dc.typeConference paper
pubs.publication-statusPublished

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
RA_hdl_107656.pdf
Size:
3.31 MB
Format:
Adobe Portable Document Format
Description:
Restricted Access
Download

Collections

Computer Science publications