Multi-scale structure aware network for salient object detection

Ge Zhu; Lei Wang

doi:10.1117/12.2646897

7 September 2022 Multi-scale structure aware network for salient object detection

Ge Zhu, Lei Wang

Proceedings Volume 12329, Third International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2022); 123293O (2022) https://doi.org/10.1117/12.2646897
Event: Third International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2022), 2022, Changsha, China

Abstract

The methods based on convolutional neural network (CNN) have greatly boosted the performance of salient object detection. However, detecting salient objects of multiple scales remains a challenge. To identify salient objects with different scales, we propose a novel multi-scale structure aware network, which can effectively integrate the semantic and detail information of multi-level features to enhance the complementarity between the features at different scales. Specifically, we first propose a global context enhancement module (GCEM) to enhance the relationship between highlevel features in CNN through the atrous spatial pyramid pooling module. Then, we utilize the channel and spatial attention mechanisms to suppress the background noises in above enhanced features. Next, we design feature integration module (FIM) to selectively fuse the low-level detail features, high-level semantic features, and global context information generated by GCEM. Finally, the proposed GCEM and FIM module are progressively cascaded three times to generate final saliency maps. Experimental results on three benchmark datasets demonstrate that our approach achieves superior performance over state-of-the-art methods.

Citation Download Citation

Ge Zhu and Lei Wang "Multi-scale structure aware network for salient object detection", Proc. SPIE 12329, Third International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2022), 123293O (7 September 2022); https://doi.org/10.1117/12.2646897

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available