• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Zhao, Lijun (Zhao, Lijun.) | Wang, Han (Wang, Han.)

收录:

EI Scopus

摘要:

It is difficult to learn global remote semantic information based on convolutional neural network, and it is difficult to obtain multi-scale feature information based on Vision Transformer, Swin Transformer and Pyramid Vision Transformer. However, salient objects maybe involve different scales. This paper introduces Shunted Transformer as the backbone network to extract multi-scale features to achieve salient object detection. Aiming at the problem of ignoring the difference between different features and dilution of high-level features when fusing high-level and low-level features, a decoder for progressive fusion of multi-scale features is designed. In addition, to solve the problem that the boundary features obtained may not match the salient object due to the separation of the boundary prediction structure and the salient object prediction branch, this paper refers to the BIG module and optimizes its feature input. Finally, the validity of the proposed model is verified by experiments on four widely used datasets. © 2023 IEEE.

关键词:

Object detection Object recognition Convolutional neural networks Semantics Feature extraction

作者机构:

  • [ 1 ] [Zhao, Lijun]School of Software Engineering, Beijing University of Technology, Beijing, China
  • [ 2 ] [Wang, Han]School of Artificial Intelligence and Automation, Beijing University of Technology, Beijing, China

通讯作者信息:

电子邮件地址:

查看成果更多字段

相关关键词:

相关文章:

来源 :

年份: 2023

页码: 179-183

语种: 英文

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 3

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 2

归属院系:

在线人数/总访问数:334/4976384
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司