Progressive Guided Fusion Network with Multi-Modal and Multi-Scale Attention for RGB-D Salient Object Detection

doi:10.1109/ACCESS.2021.3126338

CIOMP OpenIR

	Progressive Guided Fusion Network with Multi-Modal and Multi-Scale Attention for RGB-D Salient Object Detection
	J. Wu; G. Han; H. Wang; H. Yang; Q. Li; D. Liu; F. Ye and P. Liu
	2021
发表期刊	IEEE Access
ISSN	21693536
卷号	9 页码:150608-150622
摘要	The depth map contains abundant spatial structure cues, which makes it extensively introduced into saliency detection tasks for improving the detection accuracy. Nevertheless, the acquired depth map is often with uneven quality, due to the interference of depth sensors and external environments, posing a challenge when trying to minimize the disturbances from low-quality depth maps during the fusion process. In this article, to mitigate such issues and highlight the salient objects, we propose a progressive guided fusion network (PGFNet) with multi-modal and multi-scale attention for RGB-D salient object detection. Particularly, we first present a multi-modal and multi-scale attention fusion model (MMAFM) to fully mine and utilize the complementarity of features at different scales and modalities for achieving optimal fusion. Then, to strengthen the semantic expressiveness of the shallow-layer features, we design a multi-modal feature refinement mechanism (MFRM), which exploits the high-level fusion feature to guide the enhancement of the shallow-layer original RGB and depth features before they are fused. Moreover, a residual prediction module (RPM) is applied to further suppress background elements. Our entire network adopts a top-down strategy to progressively excavate and integrate valuable information. Compared with the state-of-the-art methods, experimental results demonstrate the effectiveness of our proposed method both qualitatively and quantitatively on eight challenging benchmark datasets. 2013 IEEE.
DOI	10.1109/ACCESS.2021.3126338
URL	查看原文
收录类别	SCI ; EI
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/65557
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	J. Wu,G. Han,H. Wang,et al. Progressive Guided Fusion Network with Multi-Modal and Multi-Scale Attention for RGB-D Salient Object Detection[J]. IEEE Access,2021,9:150608-150622.
APA	J. Wu.,G. Han.,H. Wang.,H. Yang.,Q. Li.,...&F. Ye and P. Liu.(2021).Progressive Guided Fusion Network with Multi-Modal and Multi-Scale Attention for RGB-D Salient Object Detection.IEEE Access,9,150608-150622.
MLA	J. Wu,et al."Progressive Guided Fusion Network with Multi-Modal and Multi-Scale Attention for RGB-D Salient Object Detection".IEEE Access 9(2021):150608-150622.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Progressive Guided F（6898KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载