Linear-Model-inspired Neural Network for Electromagnetic Inverse Scattering

TL;DR

This paper introduces a neural network inspired by linear models to improve electromagnetic inverse scattering, effectively combining model-based regularization with data-driven learning for better reconstruction accuracy.

Contribution

It proposes a novel linear-model-inspired neural network that integrates a model-driven regularizer for electromagnetic inverse scattering, enhancing solution efficiency and accuracy.

Findings

Outperforms existing methods in reconstruction quality

Demonstrates robustness across different scattering scenarios

Achieves efficient end-to-end training

Abstract

Electromagnetic inverse scattering problems (ISPs) aim to retrieve permittivities of dielectric scatterers from the scattering measurement. It is often highly nonlinear, caus-ing the problem to be very difficult to solve. To alleviate the issue, this letter exploits a linear model-based network (LMN) learning strategy, which benefits from both model complexity and data learning. By introducing a linear model for ISPs, a new model with network-driven regular-izer is proposed. For attaining efficient end-to-end learning, the network architecture and hyper-parameter estimation are presented. Experimental results validate its superiority to some state-of-the-arts.