Contrast-Source-Based Physics-Driven Neural Network for Inverse Scattering Problems
This work addresses efficiency and robustness issues in inverse scattering for applications like medical imaging or non-destructive testing, but it is incremental as it builds on existing untrained neural network methods.
The paper tackled the problem of slow inference in untrained neural networks for inverse scattering by proposing a contrast-source-based physics-driven neural network that predicts induced current distribution, achieving improved efficiency and robust reconstruction validated through simulations and experiments.
Deep neural networks (DNNs) have recently been applied to inverse scattering problems (ISPs) due to their strong nonlinear mapping capabilities. However, supervised DNN solvers require large-scale datasets, which limits their generalization in practical applications. Untrained neural networks (UNNs) address this issue by updating weights from measured electric fields and prior physical knowledge, but existing UNN solvers suffer from long inference time. To overcome these limitations, this paper proposes a contrast-source-based physics-driven neural network (CSPDNN), which predicts the induced current distribution to improve efficiency and incorporates an adaptive total variation loss for robust reconstruction under varying contrast and noise conditions. The improved imaging performance is validated through comprehensive numerical simulations and experimental data.