volume | PIER Journals

Abstract

Electromagnetic inverse scattering (EIS) problem is challenging due to its properties of strong nonlinearity and ill-posedness, where existing deep learning approaches often lack systematic network refinement and comprehensive analysis of key factors affecting performance. This work introduces CAMO-Net, a U-Net-based framework for EIS that integrates a channel-attention mechanism and systematically optimizes architectural and training factors to address these limitations. By integrating channel attention into skip connections, adopting a multi-scale channel configuration, and fine-tuning key hyperparameters through controlled experiments, CAMO-Net achieves superior accuracy and robustness. Experimental results demonstrate that it reduces the mean relative error (MRE) by 32.5% and the mean squared error (MSE) by 34.1% compared to the baseline U-Net. Our results demonstrate that joint channel attention and multi-factor optimization provide an effective, reproducible pathway for high-precision EIS imaging, offering new insights for robust reconstruction in EIS problems.

1. Cakoni, Fioralba and David Colton, "Combined far-ield operators in electromagnetic inverse scattering theory," Mathematical Methods in the Applied Sciences, Vol. 26, No. 5, 413-429, 2003.
doi:10.1002/mma.360 Google Scholar

2. Yin, Tiantian, Zhun Wei, and Xudong Chen, "Non-iterative methods based on singular value decomposition for inverse scattering problems," IEEE Transactions on Antennas and Propagation, Vol. 68, No. 6, 4764-4773, 2020.
doi:10.1109/tap.2020.2969708 Google Scholar

3. Radke, Karl Ludger, Benedikt Kamp, Vibhu Adriaenssens, Julia Stabinska, Patrik Gallinnis, Hans-Jörg Wittsack, Gerald Antoch, and Anja Müller-Lutz, "Deep learning-based denoising of CEST MR data: A feasibility study on applying synthetic phantoms in medical imaging," Diagnostics, Vol. 13, No. 21, 3326, 2023.
doi:10.3390/diagnostics13213326 Google Scholar

4. Fan, Guangpeng, Feixiang Chen, Danyu Chen, Yan Li, and Yanqi Dong, "A deep learning model for quick and accurate rock recognition with smartphones," Mobile Information Systems, Vol. 2020, No. 1, 7462524, 2020.
doi:10.1155/2020/7462524 Google Scholar

5. Wen, Zhigang, Dan Liu, Xiaoqing Liu, Ling Zhong, You Lv, and Yinglin Jia, "Deep learning based smart radar vision system for object recognition," Journal of Ambient Intelligence and Humanized Computing, Vol. 10, No. 3, 829-839, 2019.
doi:10.1007/s12652-018-0853-9 Google Scholar

6. Wang, Quanfeng, Alexander H. Paulus, Mei Song Tong, and Thomas F. Eibert, "An indoor localization technique utilizing passive tags and 3-d microwave passive radar imaging," Progress In Electromagnetics Research, Vol. 181, 89-98, 2024.
doi:10.2528/PIER24120903 Google Scholar

7. Chen, Xudong, Computational Methods for Electromagnetic Inverse Scattering, John Wiley & Sons, Singapore, 2018.
doi:10.1002/9781119311997

8. Van Den Berg, Peter M. and Ralph E. Kleinman, "A contrast source inversion method," Inverse Problems, Vol. 13, No. 6, 1607, 1997.
doi:10.1088/0266-5611/13/6/013 Google Scholar

9. Zhang, Wenji and Ahmad Hoorfar, "Reconstruction of two-dimensional permittivity distribution with distorted rytov iterative method," IEEE Antennas and Wireless Propagation Letters, Vol. 10, 1072-1075, 2011.
doi:10.1109/lawp.2011.2169643 Google Scholar

10. Devaney, A. J., "Inverse-scattering theory within the Rytov approximation," Optics Letters, Vol. 6, No. 8, 374-376, 1981.
doi:10.1364/ol.6.000374 Google Scholar

11. Habashy, Tarek M., Ross W. Groom, and Brian R. Spies, "Beyond the Born and Rytov approximations: A nonlinear approach to electromagnetic scattering," Journal of Geophysical Research: Solid Earth, Vol. 98, No. B2, 1759-1775, 1993.
doi:10.1029/92jb02324 Google Scholar

12. Wang, Yusong, Zheng Zong, Siyuan He, Rencheng Song, and Zhun Wei, "Push the generalization limitation of learning approaches by multidomain weight-sharing for full-wave inverse scattering," IEEE Transactions on Geoscience and Remote Sensing, Vol. 61, 1-14, 2023.
doi:10.1109/tgrs.2023.3303572 Google Scholar

13. Sun, Guanqun, Yizhi Pan, Weikun Kong, Zichang Xu, Jianhua Ma, Teeradaj Racharak, Le-Minh Nguyen, and Junyi Xin, "DA-TransUNet: Integrating spatial and channel dual attention with transformer U-net for medical image segmentation," Frontiers in Bioengineering and Biotechnology, Vol. 12, 1398237, 2024.
doi:10.3389/fbioe.2024.1398237 Google Scholar

14. Haberman, Boaz, "Uniqueness in Calderón's problem for conductivities with unbounded gradient," Communications in Mathematical Physics, Vol. 340, No. 2, 639-659, 2015. Google Scholar

15. Guo, Rui, Tianyao Huang, Maokun Li, Haiyang Zhang, and Yonina C. Eldar, "Physics-embedded machine learning for electromagnetic data imaging: Examining three types of data-driven imaging methods," IEEE Signal Processing Magazine, Vol. 40, No. 2, 18-31, 2023.
doi:10.1109/msp.2022.3198805 Google Scholar

16. Chen, Xudong, "Subspace-based optimization method for solving inverse-scattering problems," IEEE Transactions on Geoscience and Remote Sensing, Vol. 48, No. 1, 42-49, 2010.
doi:10.1109/tgrs.2009.2025122 Google Scholar

17. Jin, Lei, Jialei Xie, Baicao Pan, and Guoqing Luo, "Generalized phase retrieval model based on physics-inspired network for holographic metasurface (invited paper)," Progress In Electromagnetics Research, Vol. 178, 103-110, 2023.
doi:10.2528/PIER23100604 Google Scholar

18. Wang, Qilong, Banggu Wu, Pengfei Zhu, Peihua Li, Wangmeng Zuo, and Qinghua Hu, "ECA-Net: Efficient channel attention for deep convolutional neural networks," 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 11531-11539, Seattle, WA, USA, 2020.
doi:10.1109/cvpr42600.2020.01155

19. Hegazy, Ahmed M., Hegazy, Mostafa Alizadeh, Amr Samir, Mohamed Basha, and Safieddin Safavi-Naeini, "Remote material characterization with complex baseband FMCW radar sensors," Progress In Electromagnetics Research, Vol. 177, 107-126, 2023.
doi:10.2528/PIER23032403 Google Scholar

20. Hu, Jie, Li Shen, and Gang Sun, "Squeeze-and-excitation networks," 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 7132-7141, Salt Lake City, UT, USA, 2018.
doi:10.1109/cvpr.2018.00745

21. Xia, Yixin and Siyuan He, "A lightweight deep learning model for full-wave nonlinear inverse scattering problems," Progress In Electromagnetics Research M, Vol. 128, 83-88, 2024.
doi:10.2528/pierm24071701 Google Scholar

22. Hochreiter, Sepp and Jürgen Schmidhuber, "Long short-term memory," Neural Computation, Vol. 9, No. 8, 1735-1780, 1997.
doi:10.1162/neco.1997.9.8.1735 Google Scholar

23. Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton, "ImageNet classification with deep convolutional neural networks," Communications of the ACM, Vol. 60, No. 6, 84-90, 2017.
doi:10.1145/3065386 Google Scholar

24. Liu, Jianfa, Yusong Wang, Lei Jin, Bao Wang, Zheng Zong, Siyuan He, and Zhun Wei, "Exploring scaling laws in large learning models for inverse scattering with spatial-temporal diffusion," IEEE Transactions on Antennas and Propagation, 2025.
doi:10.1109/tap.2025.3569099 Google Scholar

25. Wei, Zhun and Xudong Chen, "Physics-inspired convolutional neural network for solving full-wave inverse scattering problems," IEEE Transactions on Antennas and Propagation, Vol. 67, No. 9, 6138-6148, 2019.
doi:10.1109/tap.2019.2922779 Google Scholar

Dr. Tianhao Pan

Dr. Jianfa Liu