Article: Joint training with the edge detection network for salient object detection Journal: International Journal of Computational Science and Engineering (IJCSE) 2022 Vol.25 No.5 pp.504 - 512 Abstract: The U-shaped network has great advantages in object detection tasks. However, most of the previous salient object detection studies still suffered from inaccurate predictions affected by unclear object boundaries. Considering the complementarity of the information between salient object and salient edge, we designed a new kind of network to effectively perform the joint training with edge detection tasks in three steps. Firstly, we added a prediction branch on the bottom-up pathway for capturing the edge of salient objects. Secondly, salient object features, global context, integrated low-level details, and high-level semantic information are extracted by the method of progressive fusion. Finally, the feature of the salient edge is concatenated with that of the salient object on the last layer in the top-down pathway. Since the salient edge feature contains much information about edge and location, the feature fusion can locate salient objects more accurately. The results of experiments on five benchmark datasets demonstrate that the proposed approach achieves competitive performance. Inderscience Publishers - linking academia, business and industry through research

Title: Joint training with the edge detection network for salient object detection

Authors: Gu Zongyun; Kan Junling; Ma Chun; Wang Qing; Li Fangfang

Addresses: College of Medical Information Engineering, Anhui University of Chinese Medicine, Hefei, 230012, China ' College of Medical Information Engineering, Anhui University of Chinese Medicine, Hefei, 230012, China ' College of Medical Information Engineering, Anhui University of Chinese Medicine, Hefei, 230012, China ' College of Medical Information Engineering, Anhui University of Chinese Medicine, Hefei, 230012, China ' College of Medical Information Engineering, Anhui University of Chinese Medicine, Hefei, 230012, China

Abstract: The U-shaped network has great advantages in object detection tasks. However, most of the previous salient object detection studies still suffered from inaccurate predictions affected by unclear object boundaries. Considering the complementarity of the information between salient object and salient edge, we designed a new kind of network to effectively perform the joint training with edge detection tasks in three steps. Firstly, we added a prediction branch on the bottom-up pathway for capturing the edge of salient objects. Secondly, salient object features, global context, integrated low-level details, and high-level semantic information are extracted by the method of progressive fusion. Finally, the feature of the salient edge is concatenated with that of the salient object on the last layer in the top-down pathway. Since the salient edge feature contains much information about edge and location, the feature fusion can locate salient objects more accurately. The results of experiments on five benchmark datasets demonstrate that the proposed approach achieves competitive performance.

Keywords: deep learning; salient object detection; SOD; U-shape architecture; edge detection; feature pyramid network.

DOI: 10.1504/IJCSE.2022.126253

International Journal of Computational Science and Engineering, 2022 Vol.25 No.5, pp.504 - 512

Received: 18 Dec 2020
Accepted: 01 Sep 2021
Published online: 18 Oct 2022 *

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

Title: Joint training with the edge detection network for salient object detection

Keep up-to-date