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。
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.
作者
张文明
姚振飞
高雅昆
李海滨
ZHANG Wenming;YAO Zhenfei;GAO Yakun;LI Haibin(School of Electrical Engineering,Yan Shan University,Qinhuangdao 066004,China)
出处
《电子与信息学报》
EI
CSCD
北大核心
2020年第5期1201-1208,共8页
Journal of Electronics & Information Technology
基金
河北省自然科学基金(F2015203212,F2019203195)。
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
Saliency detection
Deep learning
Decomposed convolution
Sparse cross-layer connection
Multiscale fusion
