Multi-label image classification by feature attention network

Yan, Z; Liu, W; Wen, S; Yang, Y

Multi-label image classification by feature attention network

Yan, Z Liu, W Wen, S

Yang, Y

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Access, 2019, 7, pp. 98005-98013
Issue Date:: 2019-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (15.86 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Yan, Z
dc.contributor.author	Liu, W
dc.contributor.author	Wen, S https://orcid.org/0000-0001-8077-7001
dc.contributor.author	Yang, Y
dc.date.accessioned	2022-07-18T04:04:16Z
dc.date.available	2022-07-18T04:04:16Z
dc.date.issued	2019-01-01
dc.identifier.citation	IEEE Access, 2019, 7, pp. 98005-98013
dc.identifier.issn	2169-3536
dc.identifier.issn	2169-3536
dc.identifier.uri	http://hdl.handle.net/10453/158985
dc.description.abstract	Learning the correlation among labels is a standing-problem in the multi-label image recognition task. The label correlation is the key to solve the multi-label classification but it is too abstract to model. Most solutions try to learn image label dependencies to improve multi-label classification performance. However, they have ignored two more realistic problems: object scale inconsistent and label tail (category imbalance). These two problems will impact the bad influence on the classification model. To tackle these two problems and learn the label correlations, we propose feature attention network (FAN) which contains feature refinement network and correlation learning network. FAN builds top-down feature fusion mechanism to refine more important features and learn the correlations among convolutional features from FAN to indirect learn the label dependencies. Following our proposed solution, we achieve performed classification accuracy on MSCOCO 2014 and VOC 2007 dataset.
dc.language	English
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation	National Natural Science Foundation of China61673187
dc.relation.ispartof	IEEE Access
dc.relation.isbasedon	10.1109/ACCESS.2019.2929512
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	08 Information and Computing Sciences, 09 Engineering, 10 Technology
dc.title	Multi-label image classification by feature attention network
dc.type	Journal Article
utslib.citation.volume	7
utslib.for	08 Information and Computing Sciences
utslib.for	09 Engineering
utslib.for	10 Technology
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 - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	open_access	*
dc.date.updated	2022-07-18T04:04:02Z
pubs.publication-status	Published
pubs.volume	7

Abstract:

Learning the correlation among labels is a standing-problem in the multi-label image recognition task. The label correlation is the key to solve the multi-label classification but it is too abstract to model. Most solutions try to learn image label dependencies to improve multi-label classification performance. However, they have ignored two more realistic problems: object scale inconsistent and label tail (category imbalance). These two problems will impact the bad influence on the classification model. To tackle these two problems and learn the label correlations, we propose feature attention network (FAN) which contains feature refinement network and correlation learning network. FAN builds top-down feature fusion mechanism to refine more important features and learn the correlations among convolutional features from FAN to indirect learn the label dependencies. Following our proposed solution, we achieve performed classification accuracy on MSCOCO 2014 and VOC 2007 dataset.

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

http://hdl.handle.net/10453/158985