Squeezed Bilinear Pooling for Fine-Grained Visual Categorization

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

Squeezed Bilinear Pooling for Fine-Grained Visual Categorization

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

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), 2020, 00, pp. 728-732
Issue Date:: 2020

Closed Access

	Filename	Description	Size
	09022622.pdf	Published version	490.93 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
dc.contributor.author	Wang, D
dc.contributor.author	Holewa, H
dc.contributor.author	Xu, M https://orcid.org/0000-0001-9581-8849
dc.date	2019-10-27
dc.date.accessioned	2021-04-12T11:07:56Z
dc.date.available	2021-04-12T11:07:56Z
dc.date.issued	2020
dc.identifier.citation	2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), 2020, 00, pp. 728-732
dc.identifier.isbn	9781728150239
dc.identifier.issn	2473-9936
dc.identifier.uri	http://hdl.handle.net/10453/148043
dc.description.abstract	In this paper, we propose a supervised selection based method to decrease both the computation and the feature dimension of the original bilinear pooling. Different from currently existing compressed second-order pooling methods, the proposed selection method is matrix normalization applicable. Moreover, by extracting the selected highly semantic feature channels, we proposed the Fisher- Recurrent-Attention structure and achieved state-of-the-art fine-grained classification results among the VGG-16 based models.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
dc.relation.ispartof	2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
dc.relation.ispartofseries	IEEE International Conference on Computer Vision Workshops
dc.relation.isbasedon	10.1109/iccvw.2019.00093
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Squeezed Bilinear Pooling for Fine-Grained Visual Categorization
dc.type	Conference Proceeding
utslib.citation.volume	00
utslib.location.activity	South Korea
utslib.for	0801 Artificial Intelligence and Image Processing
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/Strength - INEXT - Innovation in IT Services and Applications
pubs.organisational-group	/University of Technology Sydney/Strength - GBDTC - Global Big Data Technologies
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2021-04-12T11:07:55Z
pubs.finish-date	2019-10-28
pubs.publication-status	Published
pubs.start-date	2019-10-27
pubs.volume	00

Abstract:

In this paper, we propose a supervised selection based method to decrease both the computation and the feature dimension of the original bilinear pooling. Different from currently existing compressed second-order pooling methods, the proposed selection method is matrix normalization applicable. Moreover, by extracting the selected highly semantic feature channels, we proposed the Fisher- Recurrent-Attention structure and achieved state-of-the-art fine-grained classification results among the VGG-16 based models.

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

http://hdl.handle.net/10453/148043