Title: JALNet: joint attention learning network for RGB-D salient object detection

Authors: Xiuju Gao; Jianhua Cui; Jin Meng; Huaizhong Shi; Songsong Duan; Chenxing Xia

Addresses: School of Electrical and Information Engineering, Anhui University of Science and Technology, Huainan, Anhui, China ' Anyang Cigarette Factory, China Tobacco Henan Industrial Co., Ltd., Anyang, Henan, China ' Anyang Cigarette Factory, China Tobacco Henan Industrial Co., Ltd., Anyang, Henan, China ' Anyang Cigarette Factory, China Tobacco Henan Industrial Co., Ltd., Anyang, Henan, China ' College of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, Anhui, China ' College of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, Anhui, China

Abstract: The existing RGB-D saliency object detection (SOD) methods mostly explore the complementary information between depth features and RGB features. However, these methods ignore the bi-directional complementarity between RGB and depth features. From this view, we propose a joint attention learning network (JALNet) to learn the cross-modal mutual complementary effect between the RGB images and depth maps. Specifically, two joint attention learning networks are designed, namely, a cross-modal joint attention fusion module (JAFM) and a joint attention enhance module (JAEM), respectively. The JAFM learns cross-modal complementary information from the RGB and depth features, which can strengthen the interaction of information and complementarity of useful information. At the same time, we utilise the JAEM to enlarge receptive field information to highlight salient objects. We conducted comprehensive experiments on four public datasets, which proved that the performance of our proposed JALNet outperforms 16 state-of-the-art (SOTA) RGB-D SOD methods.

Keywords: salient object detection; depth map; bi-directional complementarity.

DOI: 10.1504/IJCSE.2024.136249

International Journal of Computational Science and Engineering, 2024 Vol.27 No.1, pp.36 - 47

Received: 19 May 2022
Received in revised form: 17 Jul 2022
Accepted: 20 Jul 2022
Published online: 25 Jan 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article