Automatic image attribute selection for zero-shot learning of object categories

Liu, Liangchen, Wiliem, Arnold, Chen, Shaokang and Lovell, Brian C. (2014). Automatic image attribute selection for zero-shot learning of object categories. In: Proceedings - International Conference on Pattern Recognition. 22nd International Conference on Pattern Recognition, ICPR 2014, Stockholm, Sweden, (2619-2624). 24-28 August, 2014. doi:10.1109/ICPR.2014.452

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
UQ348995_peer_review_other.pdf UQ348995_peer_review_other.pdf application/pdf 80.59KB 0

Author Liu, Liangchen
Wiliem, Arnold
Chen, Shaokang
Lovell, Brian C.
Title of paper Automatic image attribute selection for zero-shot learning of object categories
Conference name 22nd International Conference on Pattern Recognition, ICPR 2014
Conference location Stockholm, Sweden
Conference dates 24-28 August, 2014
Convener IEEE
Proceedings title Proceedings - International Conference on Pattern Recognition   Check publisher's open access policy
Journal name 2014 22Nd International Conference On Pattern Recognition (Icpr)   Check publisher's open access policy
Place of Publication Washington, DC, United States
Publisher I E E E Computer Society
Publication Year 2014
Year available 2014
Sub-type Fully published paper
DOI 10.1109/ICPR.2014.452
Open Access Status Not yet assessed
ISBN 9781479952083
ISSN 1051-4651
Start page 2619
End page 2624
Total pages 6
Language eng
Abstract/Summary Recently the use of image attributes as image descriptors has drawn great attention. This is because the resulting descriptors extracted using these attributes are human understandable as well as machine readable. Although the image attributes are generally semantically meaningful, they may not be discriminative. As such, prior works often consider a discriminative learning approach that could discover discriminative attributes. Nevertheless, the resulting learned attributes could lose their semantic meaning. To that end, in the present work, we study two properties of attributes: discriminative power and reliability. We then propose a novel greedy algorithm called Discriminative and Reliable Attribute Learning (DRAL) which selects a subset of attributes which maximises an objective function incorporating the two properties. We compare our proposed system to the recent state-of-the-art approach, called Direct Attribute Prediction (DAP) for the zero-shot learning task on the Animal with Attributes (AwA) dataset. The results show that our proposed approach can achieve similar performance to this state-of-the-art approach while using a significantly smaller number of attributes.
Keyword Animals
Detectors
Feature extraction
Linear programming
Relibaility
Semantics
Training
Q-Index Code E1
Q-Index Status Confirmed Code
Institutional Status UQ

Document type: Conference Paper
Sub-type: Fully published paper
Collections: Official 2015 Collection
School of Information Technology and Electrical Engineering Publications
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 2 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 6 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Tue, 13 Jan 2015, 13:51:52 EST by System User on behalf of School of Information Technol and Elec Engineering