标题:Channel-Wise Feature Response Based Deep Saliency Detection
作者:Li C.; Chen Z.; Liu C.
作者机构:[Li, C] School of Control Science and Engineering, Shandong University, Jinan, China;[ Chen, Z] School of Control Science and Engineering, Shandong Un 更多
通讯作者:Liu, C(chenzhenxue@sdu.edu.cn)
通讯作者地址:[Liu, C] School of Control Science and Engineering, Shandong UniversityChina;
来源:ICARM 2018 - 2018 3rd International Conference on Advanced Robotics and Mechatronics
出版年:2019
页码:537-541
DOI:10.1109/ICARM.2018.8610858
关键词:Channel-wise response; Feature refinement; Residual network; Saliency
摘要:Saliency detection based on deep learning has achieved excellent performance. This paper focuses on channel-wise feature response. Our model owns three structures: channel-wise extraction (CCFE), channel-wise hierarchical refinement (CHFR), and feature maps fusion (HFMF). The squeeze and excitation residual net is the base network used in this work, which can explicitly explore the dependencies among channels. CCFE is utilized to obtain global feature maps, which has a lot of information loss. Then, the CHFR structure is carried out to take advantage of spatial cues. At the end, HFMF is implemented to fuse the feature maps. The experimental results prove that the proposed algorithm has high efficiency and superior performance compared with other fourteen methods. © 2018 IEEE.
收录类别:SCOPUS
资源类型:期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85061513877&doi=10.1109%2fICARM.2018.8610858&partnerID=40&md5=a4be96a08ffb47c7a37ace565251c849
TOP