TY - GEN
T1 - Neural Contrast Source Inversion Method Based on Single-frequency Data
AU - Zeng, Jinhong
AU - Shan, Tao
AU - Li, Maokun
AU - Yang, Fan
AU - Xu, Shenheng
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - In this paper, we propose a neural contrast source iteration (Neural CSI) model to solve 2D inverse scattering problems. Inspired by the traditional contrast source iteration (CSI) method, we construct a residual convolution neural network (CNN) to learn the gradient update process. With our dataset (generated by the method of the moment), we train the residual CNN by the objective function of the traditional CSI method in an unsupervised manner.
AB - In this paper, we propose a neural contrast source iteration (Neural CSI) model to solve 2D inverse scattering problems. Inspired by the traditional contrast source iteration (CSI) method, we construct a residual convolution neural network (CNN) to learn the gradient update process. With our dataset (generated by the method of the moment), we train the residual CNN by the objective function of the traditional CSI method in an unsupervised manner.
KW - Inverse scattering problem
KW - contrast source inversion method
KW - convolutional neural network
KW - deep learning
KW - unsupervised training
UR - https://www.scopus.com/pages/publications/85151525097
U2 - 10.1109/ACES-China56081.2022.10065311
DO - 10.1109/ACES-China56081.2022.10065311
M3 - 会议稿件
AN - SCOPUS:85151525097
T3 - 2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022
BT - 2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022
Y2 - 9 December 2022 through 12 December 2022
ER -