Crowd Counting with Deep Negative Correlation Learning

Shi, Z; Zhang, L; Liu, Y; Cao, X; Ye, Y; Cheng, MM; Zheng, G

Crowd Counting with Deep Negative Correlation Learning

Shi, Z Zhang, L Liu, Y Cao, X Ye, Y Cheng, MM Zheng, G

Permalink

Publication Type:: Conference Proceeding
Citation:: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2018, pp. 5382 - 5390
Issue Date:: 2018-12-14

Closed Access

	Filename	Description	Size
	08578662.pdf	Published version	268 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	Shi, Z	en_US
dc.contributor.author	Zhang, L	en_US
dc.contributor.author	Liu, Y	en_US
dc.contributor.author	Cao, X	en_US
dc.contributor.author	Ye, Y	en_US
dc.contributor.author	Cheng, MM	en_US
dc.contributor.author	Zheng, G	en_US
dc.date.issued	2018-12-14	en_US
dc.identifier.citation	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2018, pp. 5382 - 5390	en_US
dc.identifier.isbn	9781538664209	en_US
dc.identifier.issn	1063-6919	en_US
dc.identifier.uri	http://hdl.handle.net/10453/133286
dc.description.abstract	© 2018 IEEE. Deep convolutional networks (ConvNets) have achieved unprecedented performances on many computer vision tasks. However, their adaptations to crowd counting on single images are still in their infancy and suffer from severe over-fitting. Here we propose a new learning strategy to produce generalizable features by way of deep negative correlation learning (NCL). More specifically, we deeply learn a pool of decorrelated regressors with sound generalization capabilities through managing their intrinsic diversities. Our proposed method, named decorrelated ConvNet (D-ConvNet), is end-to-end-trainable and independent of the backbone fully-convolutional network architectures. Extensive experiments on very deep VGGNet as well as our customized network structure indicate the superiority of D-ConvNet when compared with several state-of-the-art methods. Our implementation will be released at https://github.com/shizenglin/Deep-NCL.	en_US
dc.relation.ispartof	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition	en_US
dc.relation.isbasedon	10.1109/CVPR.2018.00564	en_US
dc.title	Crowd Counting with Deep Negative Correlation Learning	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/Students
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

© 2018 IEEE. Deep convolutional networks (ConvNets) have achieved unprecedented performances on many computer vision tasks. However, their adaptations to crowd counting on single images are still in their infancy and suffer from severe over-fitting. Here we propose a new learning strategy to produce generalizable features by way of deep negative correlation learning (NCL). More specifically, we deeply learn a pool of decorrelated regressors with sound generalization capabilities through managing their intrinsic diversities. Our proposed method, named decorrelated ConvNet (D-ConvNet), is end-to-end-trainable and independent of the backbone fully-convolutional network architectures. Extensive experiments on very deep VGGNet as well as our customized network structure indicate the superiority of D-ConvNet when compared with several state-of-the-art methods. Our implementation will be released at https://github.com/shizenglin/Deep-NCL.

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

http://hdl.handle.net/10453/133286