Next Article in Journal
SleepPos App: An Automated Smartphone Application for Angle Based High Resolution Sleep Position Monitoring and Treatment
Next Article in Special Issue
Staring Spotlight SAR with Nonlinear Frequency Modulation Signal and Azimuth Non-Uniform Sampling for Low Sidelobe Imaging
Previous Article in Journal
A Comparison of Three Neural Network Approaches for Estimating Joint Angles and Moments from Inertial Measurement Units
Previous Article in Special Issue
Multi-Aspect SAR Target Recognition Based on Prototypical Network with a Small Number of Training Samples
Article

CNN-LRP: Understanding Convolutional Neural Networks Performance for Target Recognition in SAR Images

1
School of Electronic Engineering, Xidian University, Xi’an 710071, China
2
School of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology, Xi’an 710021, China
3
Beijing Aerospace Automatic Control Institute, Beijing 100070, China
*
Author to whom correspondence should be addressed.
Academic Editor: Antonio Pepe
Received: 4 June 2021 / Revised: 29 June 2021 / Accepted: 30 June 2021 / Published: 1 July 2021
Target recognition is one of the most challenging tasks in synthetic aperture radar (SAR) image processing since it is highly affected by a series of pre-processing techniques which usually require sophisticated manipulation for different data and consume huge calculation resources. To alleviate this limitation, numerous deep-learning based target recognition methods are proposed, particularly combined with convolutional neural network (CNN) due to its strong capability of data abstraction and end-to-end structure. In this case, although complex pre-processing can be avoided, the inner mechanism of CNN is still unclear. Such a “black box” only tells a result but not what CNN learned from the input data, thus it is difficult for researchers to further analyze the causes of errors. Layer-wise relevance propagation (LRP) is a prevalent pixel-level rearrangement algorithm to visualize neural networks’ inner mechanism. LRP is usually applied in sparse auto-encoder with only fully-connected layers rather than CNN, but such network structure usually obtains much lower recognition accuracy than CNN. In this paper, we propose a novel LRP algorithm particularly designed for understanding CNN’s performance on SAR image target recognition. We provide a concise form of the correlation between output of a layer and weights of the next layer in CNNs. The proposed method can provide positive and negative contributions in input SAR images for CNN’s classification, viewed as a clear visual understanding of CNN’s recognition mechanism. Numerous experimental results demonstrate the proposed method outperforms common LRP. View Full-Text
Keywords: synthetic aperture radar (SAR); target recognition; layer-wise relevance propagation (LRP); convolutional neural networks (CNN) understanding synthetic aperture radar (SAR); target recognition; layer-wise relevance propagation (LRP); convolutional neural networks (CNN) understanding
Show Figures

Figure 1

MDPI and ACS Style

Zang, B.; Ding, L.; Feng, Z.; Zhu, M.; Lei, T.; Xing, M.; Zhou, X. CNN-LRP: Understanding Convolutional Neural Networks Performance for Target Recognition in SAR Images. Sensors 2021, 21, 4536. https://0-doi-org.brum.beds.ac.uk/10.3390/s21134536

AMA Style

Zang B, Ding L, Feng Z, Zhu M, Lei T, Xing M, Zhou X. CNN-LRP: Understanding Convolutional Neural Networks Performance for Target Recognition in SAR Images. Sensors. 2021; 21(13):4536. https://0-doi-org.brum.beds.ac.uk/10.3390/s21134536

Chicago/Turabian Style

Zang, Bo, Linlin Ding, Zhenpeng Feng, Mingzhe Zhu, Tao Lei, Mengdao Xing, and Xianda Zhou. 2021. "CNN-LRP: Understanding Convolutional Neural Networks Performance for Target Recognition in SAR Images" Sensors 21, no. 13: 4536. https://0-doi-org.brum.beds.ac.uk/10.3390/s21134536

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop