作者：
Zhou, Chi;Ye, Lulin;Peng, Hong;Liu, Zhicai;Wang, Jun;...
通讯作者：
Hong Peng
作者机构：
School of Electrical Engineering and Electronic Information, Xihua University, Chengdu 610039, P. R. China
Research Group of Natural Computing, Department of Computer Science and Artificial Intelligence, University of Seville, Sevilla 41012, Spain
School of Computer and Software Engineering, Xihua University, Chengdu 610039, P. R. China
通讯机构：
School of Computer and Software Engineering, Xihua University, Chengdu 610039, P. R. China
语种：
英文
关键词：
Nonlinear spiking neural P systems;deep convolutional neural networks;segmentation network
期刊：
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
ISSN：
0129-0657
年：
2024
卷：
34
期：
05
页码：
2450022
基金类别：
National Natural Science Foundation of China [62176216, 62076206]; Research Fund of Sichuan Science and Technology Project [2022ZYD0115]; Zhejiang Lab BioBit Program, China [2022BCF05
摘要：
Deep convolutional neural networks have shown advanced performance in accurately segmenting images. In this paper, an SNP-like convolutional neuron structure is introduced, abstracted from the nonlinear mechanism in nonlinear spiking neural P (NSNP) systems. Then, a U-shaped convolutional neural network named SNP-like parallel-convolutional network, or SPC-Net, is constructed for segmentation tasks. The dual-convolution concatenate (DCC) and dual-convolution addition (DCA) network blocks are designed, respectively, in the encoder and decoder stages. The two blocks employ parallel convolution with different kernel sizes to improve feature representation ability and make fu...
