OPT OpenIR  > 光学影像学习与分析中心
SalNet: Edge constraint based end-to-end model for salient object detection
Han, Le1,2; Li, Xuelong1; Dong, Yongsheng1
2018
Conference Name1st Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2018
Source PublicationPattern Recognition and Computer Vision - First Chinese Conference, PRCV 2018, Proceedings
Volume11259 LNCS
Pages186-198
Conference Date2018-11-23
Conference PlaceGuangzhou, China
PublisherSpringer Verlag
Contribution Rank1
Abstract

Salient object detection is a fundamental task in computer vision and pattern recognition. And it has been investigated by many researchers in many fields for a long time. Numerous salient object detection models based on deep learning have been designed in recent years. However, the saliency maps extracted by most of the existing models are blurry or have irregular edges. To alleviate these problems, we propose a novel approach named SalNet to detect the salient objects accurately in this paper. The architecture of the SalNet is an U-Net which can combine the features of the shallow and deep layers. Moreover, a new objective function based on the image convolution is further proposed to refine the edges of saliency maps by using a constraint on the L1 distance between edge information of the ground-truth and the saliency maps. Finally, we evaluate our proposed SalNet on benchmark datasets and compare it with the state-of-the-art algorithms. Experimental results demonstrate that the SalNet is effective and outperforms several representative methods in salient object detection task. ? Springer Nature Switzerland AG 2018.

Department光学影像学习与分析中心
DOI10.1007/978-3-030-03341-5_16
Indexed ByEI
ISBN9783030033408
Language英语
ISSN03029743;16113349
EI Accession Number20184806152345
Citation statistics
Document Type会议论文
Identifierhttp://ir.opt.ac.cn/handle/181661/30868
Collection光学影像学习与分析中心
Corresponding AuthorDong, Yongsheng
Affiliation1.Center for OPTical IMagery Analysis and Learning (OPTIMAL), Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an; Shaanxi; 710119, China;
2.University of Chinese Academy of Sciences, 19A Yuquanlu, Beijing; 100049, China
Recommended Citation
GB/T 7714
Han, Le,Li, Xuelong,Dong, Yongsheng. SalNet: Edge constraint based end-to-end model for salient object detection[C]:Springer Verlag,2018:186-198.
Files in This Item:
File Name/Size DocType Version Access License
SalNet Edge constra(2115KB)会议论文 限制开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Han, Le]'s Articles
[Li, Xuelong]'s Articles
[Dong, Yongsheng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Han, Le]'s Articles
[Li, Xuelong]'s Articles
[Dong, Yongsheng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Han, Le]'s Articles
[Li, Xuelong]'s Articles
[Dong, Yongsheng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.