Abstract
Salient object detection can simulate human visual mechanism and extract important information from pictures or videos. Aiming at the problems of imprecise salient region detection and fuzzy edge representation in existing salient object detection algorithms, a self-attention salient object detection algorithm is proposed. On the one hand, the U-shaped network is used to enhance the local and global information of different levels of feature graph to generate fine saliency graph. On the other hand, the self-attention module is used to capture the global information in order to obtain larger perceptual field of vision and context information, and generate different attention weights for salient objects and backgrounds, so as to obtain better performance. Experimental results on four widely used datasets show that the proposed method achieves competitive performance.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.