模式识别与人工智能
Friday, Apr. 4, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2022, Vol. 35 Issue (6): 526-535    DOI: 10.16451/j.cnki.issn1003-6059.202206005
Deep Learning Based Object Detection and Recognition Current Issue| Next Issue| Archive| Adv Search |
RGB-D Salient Object Detection Based on Spatial Constrained and Self-Mutual Attention
YUAN Xiao1, XIAO Yun2, JIANG Bo1,3, TANG Jin1
1. Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei 230601;
2. School of Artificial Intelligence, Anhui University, Hefei 230601;
3. Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei 230088

Download: PDF (1697 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Aiming at the problem of RGB-D salient object detection, a RGB-D salient object detection method is proposed based on pyramid spatial constrained self-mutual attention. Firstly, a spatial constrained self-mutual attention module is introduced to learn multi-modal feature representations with spatial context awareness by the complementarity of multi-modal features. Meanwhile, the pairwise relationships between the query positions and surrounding areas are calculated to integrate self-attention and mutual attention, and thus the contextual features of the two modalities are aggregated. Then, to obtain more complementary information, the pyramid structure is applied to a set of spatial constrained self-mutual attention modules to adapt to different features of the receptive field under different spatial constraints and learn local and global feature representations. Finally, the multi-modal fusion module is embedded into a two-branch encoder-decoder network model, and the RGB-D salient object detection task is solved. Experiments on four benchmark datasets show strong competitiveness of the proposed me-thod in RGB-D salient object detection.
Key wordsRGB-D Salient Object Detection      Multi-modal Fusion      Self-Attention Mechanism      Convolution Neural Network     
Received: 27 August 2021     
ZTFLH: TP 391  
Fund:National Natural Science Foundation of China(No.62076004,62006002), Youth Program of Natural Science Foundation of Anhui Province(No.1908085QF264), The University Synergy Innovation Program of Anhui Province(No.GXXT-2020-013)
Corresponding Authors: JIANG Bo, Ph.D., associate professor. His research interests include image feature extraction and matching, graph data representation and learning.   
About author:: YUAN Xiao, master student. Her research interests include saliency detection.
XIAO Yun, Ph.D., associate professor. Her research interests include salient object detection and multi-modal analysis.
TANG Jin, Ph.D., professor. His research interests include image and video re-presentation and recognition, and multi-modal analysis.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
YUAN Xiao
XIAO Yun
JIANG Bo
TANG Jin
Cite this article:   
YUAN Xiao,XIAO Yun,JIANG Bo等. RGB-D Salient Object Detection Based on Spatial Constrained and Self-Mutual Attention[J]. Pattern Recognition and Artificial Intelligence, 2022, 35(6): 526-535.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202206005      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2022/V35/I6/526
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn