姚振飞,
高雅昆,,
李海滨
燕山大学电气工程学院 秦皇岛 066004
基金项目:河北省自然科学基金(F2015203212, F2019203195)
详细信息
作者简介:张文明：男，1979年生，副教授，研究方向为工业过程控制、机器视觉
姚振飞：男，1992年生，硕士生，研究方向为机器视觉与图像处理
高雅昆：男，1988年生，博士生，研究方向为机器视觉与图像处理
李海滨：男，1978年生，教授，研究方向为工业过程控制.、机器视觉、人工智能
通讯作者:高雅昆 gaoyakun6@163.com
中图分类号:TN911.73; TP391.41计量
文章访问数:2988
HTML全文浏览量:3043
PDF下载量:111
被引次数:0
出版历程
收稿日期:2019-04-08
修回日期:2019-08-30
网络出版日期:2020-01-21
刊出日期:2020-06-04
A Deep Convolutional Network for Saliency Object Detection with Balanced Accuracy and High Efficiency
Wenming ZHANG,Zhenfei YAO,
Yakun GAO,,
Haibin LI
School of Electrical Engineering, Yan Shan University, Qinhuangdao 066004, China
Funds:The Nature Science Foundation of Hebei Province (F2015203212, F2019203195)
摘要
摘要:当前的显著性目标检测算法在准确性和高效性两方面不能实现良好的平衡，针对这一问题，该文提出了一种新的平衡准确性以及高效性的显著性目标检测深度卷积网络模型。首先，通过将传统的卷积替换为可分解卷积，大幅减少计算量，提高检测效率。其次，为了更好地利用不同尺度的特征，采用了稀疏跨层连接结构及多尺度融合结构来提高模型检测精度。广泛的评价表明，与现有方法相比，所提的算法在效率和精度上都取得了领先的性能。
关键词:显著性检测/
深度学习/
分解卷积/
稀疏跨层连接/
多尺度融合
Abstract:It is difficult for current salient object detection algorithms to reach a good balance performance between accuracy and efficiency. To solve this problem, a deep convolutional network for saliency object detection with balanced accuracy and high efficiency is produced. First, through replacing the traditional convolution with the decomposed convolution, the computational complexity is greatly reduced and the detection efficiency of the model is improved. Second, in order to make better use of the characteristics of different scales, sparse cross-layer connection structure and multi-scale fusion structure are adopted to improve the detection precision. A wide range of evaluations show that compared with the existing methods, the proposed algorithm achieves the leading performance in efficiency and accuracy.
Key words:Saliency detection/
Deep learning/
Decomposed convolution/
Sparse cross-layer connection/
Multi-scale fusion
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=c98312a3-9280-48b2-8923-f24ce6a5612c
