Subset feature learning for fine-grained category classification

Ge, Zong Yuan, McCool, Christopher, Sanderson, Conrad and Corke, Peter (2015). Subset feature learning for fine-grained category classification. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015. IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015, Boston, MA, United States, (46-52). 7-12 June, 2015. doi:10.1109/CVPRW.2015.7301271

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Ge, Zong Yuan
McCool, Christopher
Sanderson, Conrad
Corke, Peter
Title of paper Subset feature learning for fine-grained category classification
Conference name IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015
Conference location Boston, MA, United States
Conference dates 7-12 June, 2015
Proceedings title 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015   Check publisher's open access policy
Journal name IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops   Check publisher's open access policy
Series IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Publisher IEEE Computer Society
Publication Year 2015
Sub-type Fully published paper
DOI 10.1109/CVPRW.2015.7301271
Open Access Status Not Open Access
ISBN 9781467367592
ISSN 2160-7508
Volume 2015-October
Start page 46
End page 52
Total pages 7
Collection year 2016
Language eng
Abstract/Summary Email Print Request Permissions Fine-grained categorisation has been a challenging problem due to small inter-class variation, large intra-class variation and low number of training images. We propose a learning system which first clusters visually similar classes and then learns deep convolutional neural network features specific to each subset. Experiments on the popular fine-grained Caltech-UCSD bird dataset show that the proposed method outperforms recent fine-grained categorisation methods under the most difficult setting: no bounding boxes are presented at test time. It achieves a mean accuracy of 77.5%, compared to the previous best performance of 73.2%. We also show that progressive transfer learning allows us to first learn domain-generic features (for bird classification) which can then be adapted to specific set of bird classes, yielding improvements in accuracy.
Keyword Accuracy
Australia
Birds
Feature extraction
Learning systems
Neural networks
Training
Q-Index Code EX
Q-Index Status Provisional Code
Institutional Status UQ

 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 1 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Tue, 12 Jan 2016, 11:14:06 EST by System User on behalf of Learning and Research Services (UQ Library)