DISC: Deep Image Saliency Computing via Progressive Representation Learning

doi:10.1109/TNNLS.2015.2506664

OPT OpenIR > 光谱成像技术研究室

	DISC: Deep Image Saliency Computing via Progressive Representation Learning
	Chen, Tianshui 1; Lin, Liang 1; Liu, Lingbo 1; Luo, Xiaonan 1; Li, Xuelong2
作者部门	光学影像学习与分析中心
	2016-06-01
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
卷号	27 期号:6 页码:1135-1149
产权排序	2
摘要	Salient object detection increasingly receives attention as an important component or step in several pattern recognition and image processing tasks. Although a variety of powerful saliency models have been intensively proposed, they usually involve heavy feature (or model) engineering based on priors (or assumptions) about the properties of objects and backgrounds. Inspired by the effectiveness of recently developed feature learning, we provide a novel deep image saliency computing (DISC) framework for fine-grained image saliency computing. In particular, we model the image saliency from both the coarse- and fine-level observations, and utilize the deep convolutional neural network (CNN) to learn the saliency representation in a progressive manner. In particular, our saliency model is built upon two stacked CNNs. The first CNN generates a coarse-level saliency map by taking the overall image as the input, roughly identifying saliency regions in the global context. Furthermore, we integrate superpixel-based local context information in the first CNN to refine the coarse-level saliency map. Guided by the coarse saliency map, the second CNN focuses on the local context to produce fine-grained and accurate saliency map while preserving object details. For a testing image, the two CNNs collaboratively conduct the saliency computing in one shot. Our DISC framework is capable of uniformly highlighting the objects of interest from complex background while preserving well object details. Extensive experiments on several standard benchmarks suggest that DISC outperforms other state-of-the-art methods and it also generalizes well across data sets without additional training. The executable version of DISC is available online: http://vision.sysu.edu.cn/projects/DISC.
文章类型	Article
关键词	Convolutional Neural Network (Cnn) Image Labeling Representation Learning Saliency Detection
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TNNLS.2015.2506664
收录类别	SCI ; EI
关键词[WOS]	VISUAL-ATTENTION ; OBJECT DETECTION ; PERSON REIDENTIFICATION ; REGION DETECTION ; NETWORK
语种	英语
WOS研究方向	Computer Science ; Engineering
项目资助者	National Natural Science Foundation of China(61320106008 ; Guangdong Natural Science Foundation(S2013050014548) ; Guangdong Science and Technology Program(2013B010406005 ; 61232011) ; 2015B010128009)
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000377113300003
引用统计	被引频次：119[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.opt.ac.cn/handle/181661/28146
专题	光谱成像技术研究室
作者单位	1.Sun Yat Sen Univ, Sch Data & Comp Sci, Guangzhou 510006, Guangdong, Peoples R China 2.Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Ctr Opt IMagery Anal & Learning OPTIMAL, Xian 710119, Shaanxi, Peoples R China
推荐引用方式 GB/T 7714	Chen, Tianshui,Lin, Liang,Liu, Lingbo,et al. DISC: Deep Image Saliency Computing via Progressive Representation Learning[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2016,27(6):1135-1149.
APA	Chen, Tianshui,Lin, Liang,Liu, Lingbo,Luo, Xiaonan,&Li, Xuelong.(2016).DISC: Deep Image Saliency Computing via Progressive Representation Learning.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,27(6),1135-1149.
MLA	Chen, Tianshui,et al."DISC: Deep Image Saliency Computing via Progressive Representation Learning".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 27.6(2016):1135-1149.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
DISC_ Deep Image Sal（4845KB）	期刊论文	作者接受稿	限制开放	CC BY-NC-SA	请求全文