Decomposition and Completion Network for Salient Object Detection

doi:10.1109/TIP.2021.3093380

	Decomposition and Completion Network for Salient Object Detection
	Wu, Zhe 1; Su, Li 2; Huang, Qingming 1,2,3
	2021
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	30 页码:6226-6239
摘要	Recently, fully convolutional networks (FCNs) have made great progress in the task of salient object detection and existing state-of-the-arts methods mainly focus on how to integrate edge information in deep aggregation models. In this paper, we propose a novel Decomposition and Completion Network (DCN), which integrates edge and skeleton as complementary information and models the integrity of salient objects in two stages. In the decomposition network, we propose a cross multi-branch decoder, which iteratively takes advantage of cross-task aggregation and cross-layer aggregation to integrate multi-level multi-task features and predict saliency, edge, and skeleton maps simultaneously. In the completion network, edge and skeleton maps are further utilized to fill flaws and suppress noises in saliency maps via hierarchical structure-aware feature learning and multi-scale feature completion. Through jointly learning with edge and skeleton information for localizing boundaries and interiors of salient objects respectively, the proposed network generates precise saliency maps with uniformly and completely segmented salient objects. Experiments conducted on five benchmark datasets demonstrate that the proposed model outperforms existing networks. Furthermore, we extend the proposed model to the task of RGB-D salient object detection, and it also achieves state-of-the-art performance. The code is available at https://github.com/wuzhe71/DCN.
关键词	Image edge detection Skeleton Task analysis Object detection Predictive models Feature extraction Decoding Salient object detection cross-task aggregation cross-layer aggregation saliency completion
DOI	10.1109/TIP.2021.3093380
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2018AAA0102003] ; National Natural Science Foundation of China[61931008] ; National Natural Science Foundation of China[61472389] ; China Postdoctoral Science Foundation[2020M682829]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000673531400001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：57[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/17496
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Su, Li
作者单位	1.Peng Cheng Lab, Shenzhen 518057, Peoples R China 2.Univ Chinese Acad Sci UCAS, Sch Comp Sci & Technol, Beijing 101408, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, CAS, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Wu, Zhe,Su, Li,Huang, Qingming. Decomposition and Completion Network for Salient Object Detection[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2021,30:6226-6239.
APA	Wu, Zhe,Su, Li,&Huang, Qingming.(2021).Decomposition and Completion Network for Salient Object Detection.IEEE TRANSACTIONS ON IMAGE PROCESSING,30,6226-6239.
MLA	Wu, Zhe,et al."Decomposition and Completion Network for Salient Object Detection".IEEE TRANSACTIONS ON IMAGE PROCESSING 30(2021):6226-6239.