DPANet: Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detection

doi:10.1109/TIP.2020.3028289

	DPANet: Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detection
	Chen, Zuyao 1; Cong, Runmin 2,3,4; Xu, Qianqian 5; Huang, Qingming 6,7,8,9
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2021
卷号	30 页码:7012-7024
关键词	Logic gates Object detection Contamination Task analysis Saliency detection Computer science Image color analysis Salient object detection RGB-D images depth potentiality perception gated multi-modality attention
ISSN号	1057-7149
DOI	10.1109/TIP.2020.3028289
英文摘要	There are two main issues in RGB-D salient object detection: (1) how to effectively integrate the complementarity from the cross-modal RGB-D data; (2) how to prevent the contamination effect from the unreliable depth map. In fact, these two problems are linked and intertwined, but the previous methods tend to focus only on the first problem and ignore the consideration of depth map quality, which may yield the model fall into the sub-optimal state. In this paper, we address these two issues in a holistic model synergistically, and propose a novel network named DPANet to explicitly model the potentiality of the depth map and effectively integrate the cross-modal complementarity. By introducing the depth potentiality perception, the network can perceive the potentiality of depth information in a learning-based manner, and guide the fusion process of two modal data to prevent the contamination occurred. The gated multi-modality attention module in the fusion process exploits the attention mechanism with a gate controller to capture long-range dependencies from a cross-modal perspective. Experimental results compared with 16 state-of-the-art methods on 8 datasets demonstrate the validity of the proposed approach both quantitatively and qualitatively. https://github.com/JosephChenHub/DPANet
资助项目	National Key Research and Development Program of China[2018AAA0102003] ; Beijing Nova Program[Z201100006820016] ; National Natural Science Foundation of China[61931008] ; National Natural Science Foundation of China[62002014] ; National Natural Science Foundation of China[61620106009] ; National Natural Science Foundation of China[U1636214] ; National Natural Science Foundation of China[61836002] ; National Natural Science Foundation of China[61672514] ; National Natural Science Foundation of China[61976202] ; Key Research Program of Frontier Sciences[CAS: QYZDJ-SSW-SYS013] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDB28000000] ; Beijing Natural Science Foundation[4182079] ; Youth Innovation Promotion Association CAS ; Hong Kong Scholars Program ; Elite Scientist Sponsorship Program - Beijing Association for Science and Technology ; China Postdoctoral Science Foundation[2020T130050] ; China Postdoctoral Science Foundation[2019M660438] ; Fundamental Research Funds for the Central Universities[2019RC039] ; CAAI-Huawei MindSpore Open Fund
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000683985500001
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/17298]
专题	中国科学院计算技术研究所
通讯作者	Xu, Qianqian; Huang, Qingming
作者单位	1.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100190, Peoples R China 2.Beijing Jiaotong Univ, Inst Informat Sci, Beijing 100044, Peoples R China 3.Beijing Key Lab Adv Informat Sci & Network Techno, Beijing 100044, Peoples R China 4.CUNY, Dept Comp Sci, Hong Kong, Peoples R China 5.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 6.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China 7.Univ Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management BDKM, Beijing 101408, Peoples R China 8.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 9.Peng Cheng Lab, Shenzhen 518055, Peoples R China
推荐引用方式 GB/T 7714	Chen, Zuyao,Cong, Runmin,Xu, Qianqian,et al. DPANet: Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detection[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2021,30:7012-7024.
APA	Chen, Zuyao,Cong, Runmin,Xu, Qianqian,&Huang, Qingming.(2021).DPANet: Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detection.IEEE TRANSACTIONS ON IMAGE PROCESSING,30,7012-7024.
MLA	Chen, Zuyao,et al."DPANet: Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detection".IEEE TRANSACTIONS ON IMAGE PROCESSING 30(2021):7012-7024.