A Novel Attention-Based Network for Fast Salient Object Detection

 

Author :  Bin Zhang, Yang Wu, Xiaojing Zhang and Ming Ma

Affiliation :  Inner Mongolian University

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  11, 22, December, 2021

Abstract :

In the current salient object detection network, the most popular method is using U-shape structure. However, the massive number of parameters leads to more consumption of computing and storage resources which are not feasible to deploy on the limited memory device. Some others shallow layer network will not maintain the same accuracy compared with U-shape structure and the deep network structure with more parameters will not converge to a global minimum loss with great speed. To overcome all of these disadvantages, we propose a new deep convolution network architecture with three contributions: (1) using smaller convolution neural networks (CNNs) to compress the model in our improved salient object features compression and reinforcement extraction module (ISFCREM) to reduce parameters of the model. 

Keyword :  Salient Object Detection, Optimization Strategy, Deep Learning, Model Compression, Vision Attention

For More Details:https://allconferencecfpalerts.com/cfp/view-paper.php?eno=5242