Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Unrolled convolutional neural network for full-wave inverse scattering

Abstract : An unrolled deep learning scheme for solving the full-wave nonlinear inverse scattering problems (ISPs) is pro- posed. Inspired by the so-called unrolled method, an iterative neural network structure combining contrast source inversion (CSI) method and residual network (ResNet) is designed. By embedding the CSI iterations into the deep learning model, the domain knowledge is well incorporated into the learning process. Thorough numerical tests are carried out to evaluate the performance, stability, robustness and reliability of the proposed approach. Comparisons with the widely used U-net structure and CSI exhibit the advantage of the proposed model.
Complete list of metadata

https://hal-centralesupelec.archives-ouvertes.fr/hal-03694636
Contributor : Dominique Lesselier Connect in order to contact the contributor
Submitted on : Monday, June 13, 2022 - 7:01:08 PM
Last modification on : Thursday, June 30, 2022 - 3:09:55 AM

Identifiers

  • HAL Id : hal-03694636, version 1

Citation

Yarui Zhang, Marc Lambert, Aurélia Fraysse, Dominique Lesselier. Unrolled convolutional neural network for full-wave inverse scattering. 2022. ⟨hal-03694636⟩

Share

Metrics

Record views

0