Multilabel Image Classification with Regional Latent Semantic Dependencies

Zhang, J; Wu, Q; Shen, C; Lu, J

Multilabel Image Classification with Regional Latent Semantic Dependencies

Zhang, J

Wu, Q Shen, C Lu, J

Permalink

Publication Type:: Journal Article
Citation:: IEEE Transactions on Multimedia, 2018, 20 (10), pp. 2801 - 2813
Issue Date:: 2018-10-01

Closed Access

	Filename	Description	Size
	08310600-final published version.pdf	Published Version	2.49 MB	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	Zhang, J https://orcid.org/0000-0002-0033-0494	en_US
dc.contributor.author	Wu, Q	en_US
dc.contributor.author	Shen, C	en_US
dc.contributor.author	Lu, J	en_US
dc.date.issued	2018-10-01	en_US
dc.identifier.citation	IEEE Transactions on Multimedia, 2018, 20 (10), pp. 2801 - 2813	en_US
dc.identifier.issn	1520-9210	en_US
dc.identifier.uri	http://hdl.handle.net/10453/125562
dc.description.abstract	© 1999-2012 IEEE. Deep convolution neural networks (CNNs) have demonstrated advanced performance on single-label image classification, and various progress also has been made to apply CNN methods on multilabel image classification, which requires annotating objects, attributes, scene categories, etc., in a single shot. Recent state-of-the-art approaches to the multilabel image classification exploit the label dependencies in an image, at the global level, largely improving the labeling capacity. However, predicting small objects and visual concepts is still challenging due to the limited discrimination of the global visual features. In this paper, we propose a regional latent semantic dependencies model (RLSD) to address this problem. The utilized model includes a fully convolutional localization architecture to localize the regions that may contain multiple highly dependent labels. The localized regions are further sent to the recurrent neural networks to characterize the latent semantic dependencies at the regional level. Experimental results on several benchmark datasets show that our proposed model achieves the best performance compared to the state-of-the-art models, especially for predicting small objects occurring in the images. Also, we set up an upper bound model (RLSD+ft-RPN) using bounding-box coordinates during training, and the experimental results also show that our RLSD can approach the upper bound without using the bounding-box annotations, which is more realistic in the real world.	en_US
dc.relation.ispartof	IEEE Transactions on Multimedia	en_US
dc.relation.isbasedon	10.1109/TMM.2018.2812605	en_US
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.title	Multilabel Image Classification with Regional Latent Semantic Dependencies	en_US
dc.type	Journal Article
utslib.citation.volume	10	en_US
utslib.citation.volume	20	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	08 Information and Computing Sciences	en_US
utslib.for	09 Engineering	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/Students
utslib.copyright.status	closed_access	*
pubs.issue	10	en_US
pubs.publication-status	Published	en_US
pubs.volume	20	en_US

Abstract:

© 1999-2012 IEEE. Deep convolution neural networks (CNNs) have demonstrated advanced performance on single-label image classification, and various progress also has been made to apply CNN methods on multilabel image classification, which requires annotating objects, attributes, scene categories, etc., in a single shot. Recent state-of-the-art approaches to the multilabel image classification exploit the label dependencies in an image, at the global level, largely improving the labeling capacity. However, predicting small objects and visual concepts is still challenging due to the limited discrimination of the global visual features. In this paper, we propose a regional latent semantic dependencies model (RLSD) to address this problem. The utilized model includes a fully convolutional localization architecture to localize the regions that may contain multiple highly dependent labels. The localized regions are further sent to the recurrent neural networks to characterize the latent semantic dependencies at the regional level. Experimental results on several benchmark datasets show that our proposed model achieves the best performance compared to the state-of-the-art models, especially for predicting small objects occurring in the images. Also, we set up an upper bound model (RLSD+ft-RPN) using bounding-box coordinates during training, and the experimental results also show that our RLSD can approach the upper bound without using the bounding-box annotations, which is more realistic in the real world.

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

http://hdl.handle.net/10453/125562