volume | PIER Journals

Abstract

Nowadays, deep learning schemes (DLSs) have gradually become one of the most important tools for solving inverse scattering problems (ISPs). Among DLSs, the dominant current scheme (DCS), which extracts physical features from the dominant components of the induced currents, has shown its successes by simplifying the learning process in solving ISPs. It has shown excellent performance in terms of efficiency and accuracy, but the increasing number of channels in DCS often requires higher computational costs and memory usage. In this paper, a lightweight deep learning model for DCS is proposed to reduce the burden of memories in the training and testing processes of network structure. And extensive tests of the model are conducted, where comparisons with results from the U-Net structure are provided. The comparison results validate its potential application in utilizing DCS under limited resource conditions.

1. Khoshdel, Vahab, Mohhamad Asefi, Ahmed Ashraf, and Joe LoVetri, "A multi-branch deep convolutional fusion architecture for 3D microwave inverse scattering: Stored grain application," Neural Computing and Applications, Vol. 33, 13467-13479, 2021. Google Scholar

2. Quarteroni, Alfio, Luca Formaggia, and Alessandro Veneziani, Complex Systems in Biomedicine, Springer, Milan, Italy, 2006.
doi:10.1007/88-470-0396-2

3. Mao, Weijian, Wuqun Li, and Wei Ouyang, "Review of seismic inverse scattering migration and inversion," Reviews of Geophysics and Planetary Physics, Vol. 52, No. 1, 27-44, 2021. Google Scholar

4. Ding, K., S. G. Song, and Z. Q. Xie, "Development and future application of inverse scattering theory," Progress in Geophysics (in Chinese), Vol. 20, No. 3, 661-666, 2005. Google Scholar

5. Fang, X. Z., F. L. Niu, and D. Wu, "Least-squares reverse-time migration enhanced with the inverse scattering imaging condition," Chinese Journal of Geophysics, Vol. 61, No. 9, 3770-3782, 2018. Google Scholar

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

7. Zhou, Huilin, Xin Huang, and Yuhao Wang, "Nonlinear inverse scattering imaging method based on iterative multi-scale network," Chinese Journal of Radio Science, Vol. 37, No. 6, 1019-1024, 2022. Google Scholar

8. Li, Lianlin, Long Gang Wang, Fernando L. Teixeira, Che Liu, Arye Nehorai, and Tie Jun Cui, "DeepNIS: Deep neural network for nonlinear electromagnetic inverse scattering," IEEE Transactions on Antennas and Propagation, Vol. 67, No. 3, 1819-1825, 2018. Google Scholar

9. Sun, Yu, Zhihao Xia, and Ulugbek S. Kamilov, "Efficient and accurate inversion of multiple scattering with deep learning," Optics Express, Vol. 26, No. 11, 14678-14688, 2018. Google Scholar

10. Massa, Andrea, Davide Marcantonio, Xudong Chen, Maokun Li, and Marco Salucci, "DNNs as applied to electromagnetics, antennas, and propagation - A review," IEEE Antennas and Wireless Propagation Letters, Vol. 18, No. 11, 2225-2229, 2019. Google Scholar

11. Chen, Xudong, Zhun Wei, Maokun Li, and Paolo Rocca, "A review of deep learning approaches for inverse scattering problems (invited review)," Electromagnetic Waves, Vol. 167, 67-81, 2020.
doi:10.2528/PIER20030705 Google Scholar

12. Sanghvi, Yash, Yaswanth Kalepu, and Uday K. Khankhoje, "Embedding deep learning in inverse scattering problems," IEEE Transactions on Computational Imaging, Vol. 6, 46-56, 2019. Google Scholar

13. Chen, Guanbo, Pratik Shah, John Stang, and Mahta Moghaddam, "Learning-assisted multimodality dielectric imaging," IEEE Transactions on Antennas and Propagation, Vol. 68, No. 3, 2356-2369, 2019. Google Scholar

14. Guo, Rui, Xiaoqian Song, Maokun Li, Fan Yang, Shenheng Xu, and Aria Abubakar, "Supervised descent learning technique for 2-D microwave imaging," IEEE Transactions on Antennas and Propagation, Vol. 67, No. 5, 3550-3554, 2019. Google Scholar

15. Wang, Yusong, Zheng Zong, Siyuan He, Rencheng Song, and Zhun Wei, "Push the generalization limitation of learning approaches by multi-domain weight-sharing for full-wave inverse scattering," IEEE Transactions on Geoscience and Remote Sensing, Vol. 61, 2003814, 2023. Google Scholar

16. 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. Google Scholar

17. Liu, Yu, Hao Zhao, Rencheng Song, Xudong Chen, Chang Li, and Xun Chen, "SOM-Net: Unrolling the subspace-based optimization for solving full-wave inverse scattering problems," IEEE Transactions on Geoscience and Remote Sensing, Vol. 60, 1-15, 2022. Google Scholar

18. Liu, Yongmin, Yi Zhang, Lingxuan Ouyang, and Tingting Shi, "Design of lightweight fundus lesion segmentation algorithm based on improved U-Net," Electric Measurement Technology, Vol. 47, No. 3, 127-134, 2024. Google Scholar

19. Pang, Bo, Lianghong Chen, Qingchuan Tao, Enhui Wang, and Yanmei Yu, "GA-UNet: A lightweight ghost and attention U-Net for medical image segmentation," Journal of Imaging Informatics in Medicine, Vol. 37, 1874-1888, 2024. Google Scholar

20. Deng, Yunjiao, Yulei Hou, Jiangtao Yan, and Daxing Zeng, "ELU-Net: An efficient and lightweight U-Net for medical image segmentation," IEEE Access, Vol. 10, 35932-35941, 2022. Google Scholar

21. Yang, Hao, Dinghao Zhang, Shiyin Qin, Tiejun Cui, and Jungang Miao, "Real-time detection of concealed threats with passive millimeter wave and visible images via deep neural networks," Sensors, Vol. 21, No. 24, 8456, 2021.
doi:10.3390/s21248456 Google Scholar

22. Li, Lianwei and Shiyin Qin, "Real-time detection of hiding contraband in human body during the security check based on lightweight U-Net with deep learning," Journal of Electronics & Information Technology, Vol. 44, No. 10, 3435-3446, 2022. Google Scholar

23. Zhou, Qiaoli, Li Ma, Liying Cao, and Helong Yu, "Identification of tomato leaf diseases based on improved lightweight convolutional neural networks MobileNetV3," Smart Agriculture, Vol. 4, No. 1, 47, 2022. Google Scholar

24. Shi, Hui, Dongyuan Shi, Shengjie Wang, Wei Li, Haojun Wen, and Hongtao Deng, "Crop plant automatic detecting based on in-field images by lightweight DFU-Net model," Computers and Electronics in Agriculture, Vol. 217, 108649, 2024. Google Scholar

25. Hu, L. Y., T. Zhou, W. Xu, Z. M. Wang, and Y. K. Pei, "An improved SqueezeNet lightweight model for tomato disease recognition," Journal of Zhengzhou University (Natural Science Edition), Vol. 54, No. 4, 71-77, 2022. Google Scholar

26. Wei, Zhun and Xudong Chen, "Deep-learning schemes for full-wave nonlinear inverse scattering problems," IEEE Transactions on Geoscience and Remote Sensing, Vol. 57, No. 4, 1849-1860, 2018. Google Scholar

27. He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun, "Deep residual learning for image recognition," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770-778, Las Vegas, NV, USA, 2016.

28. Jin, Kyong Hwan, Michael T. McCann, Emmanuel Froustey, and Michael Unser, "Deep convolutional neural network for inverse problems in imaging," IEEE Transactions on Image Processing, Vol. 26, No. 9, 4509-4522, 2017. Google Scholar

29. Xie, Juanying and Kaiyun Zhang, "XR-MSF-Unet: Automatic segmentation model for COVID-19 lung CT images," Journal of Frontiers of Computer Science & Technology, Vol. 16, No. 8, 1850, 2022. Google Scholar

30. Johnson, Justin, Alexandre Alahi, and Li Fei-Fei, "Perceptual losses for real-time style transfer and super-resolution," Computer Vision - ECCV 2016: 14th European Conference, 694-711, Amsterdam, The Netherlands, 2016.

Dr. Yixin Xia

Mr. Siyuan He