Fine-Grained Categorization by Deep Part-Collaboration Convolution Net

Liao, Q; Xu, M; Wang, D; Holewa, H

Fine-Grained Categorization by Deep Part-Collaboration Convolution Net

Liao, Q Xu, M

Wang, D Holewa, H

Permalink

Publication Type:: Conference Proceeding
Citation:: 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018, 2019
Issue Date:: 2019-01-16

Closed Access

	Filename	Description	Size
	08615855.pdf	Published version	923.25 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Liao, Q	en_US
dc.contributor.author	Xu, M https://orcid.org/0000-0001-9581-8849	en_US
dc.contributor.author	Wang, D	en_US
dc.contributor.author	Holewa, H	en_US
dc.date.issued	2019-01-16	en_US
dc.identifier.citation	2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018, 2019	en_US
dc.identifier.isbn	9781538666029	en_US
dc.identifier.uri	http://hdl.handle.net/10453/133519
dc.description.abstract	© 2018 IEEE. In part-based categorization context, the ability to learn representative feature from quantitative tiny object parts is of similar importance as to exactly localize the parts. We propose a new deep net structure for fine-grained categorization that follows the taxonomy workflow, which makes it interpretable and understandable for humans. By training customized sub-nets on each manually annotated parts, we increased the state-of-the-art part-based classification accuracy for general fine-grained CUB-200-2011 dataset by 2.1%. Our study shows the proposed method can produce more activation to discriminate detail part difference while maintaining high computing performance by applying a set of strategies to optimize the deep net structure.	en_US
dc.relation.ispartof	2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018	en_US
dc.relation.isbasedon	10.1109/DICTA.2018.8615855	en_US
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Fine-Grained Categorization by Deep Part-Collaboration Convolution Net	en_US
dc.type	Conference Proceeding
utslib.for	0801 Artificial Intelligence and Image Processing	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
pubs.organisational-group	/University of Technology Sydney/Students
utslib.copyright.status	closed_access	*
pubs.publication-status	Published	en_US

Abstract:

© 2018 IEEE. In part-based categorization context, the ability to learn representative feature from quantitative tiny object parts is of similar importance as to exactly localize the parts. We propose a new deep net structure for fine-grained categorization that follows the taxonomy workflow, which makes it interpretable and understandable for humans. By training customized sub-nets on each manually annotated parts, we increased the state-of-the-art part-based classification accuracy for general fine-grained CUB-200-2011 dataset by 2.1%. Our study shows the proposed method can produce more activation to discriminate detail part difference while maintaining high computing performance by applying a set of strategies to optimize the deep net structure.

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

http://hdl.handle.net/10453/133519