C-RISE: A Post-Hoc Interpretation Method of Black-Box Models for SAR ATR
-
Published:2023-06-14
Issue:12
Volume:15
Page:3103
-
ISSN:2072-4292
-
Container-title:Remote Sensing
-
language:en
-
Short-container-title:Remote Sensing
Author:
Zhu Mingzhe1ORCID, Cheng Jie1ORCID, Lei Tao2ORCID, Feng Zhenpeng1ORCID, Zhou Xianda3, Liu Yuanjing1, Chen Zhihan1
Affiliation:
1. School of Electronic Engineering, Xidian University, Xi’an 710071, China 2. Shaanxi Joint Laboratory of Artificial Intelligence, Shaanxi University of Science and Technology, Xi’an 710021, China 3. National Key Laboratory of Science and Technology on Aerospace Intelligence Control, Beijing Aerospace Automatic Control Institute, Beijing 100854, China
Abstract
The integration of deep learning methods, especially Convolutional Neural Networks (CNN), and Synthetic Aperture Radar Automatic Target Recognition (SAR ATR) has been widely deployed in the field of radar signal processing. Nevertheless, these methods are frequently regarded as black-box models due to the limited visual interpretation of their internal feature representation and parameter organization. In this paper, we propose an innovative approach named C-RISE, which builds upon the RISE algorithm to provide a post-hoc interpretation technique for black-box models used in SAR Images Target Recognition. C-RISE generates saliency maps that effectively visualize the significance of each pixel. Our algorithm outperforms RISE by clustering masks that capture similar fusion features into distinct groups, enabling more appropriate weight distribution and increased focus on the target area. Furthermore, we employ Gaussian blur to process the masked area, preserving the original image structure with optimal consistency and integrity. C-RISE has been extensively evaluated through experiments, and the results demonstrate superior performance over other interpretation methods based on perturbation when applied to neural networks for SAR image target recognition. Furthermore, our approach is highly robust and transferable compared to other interpretable algorithms, including white-box methods.
Funder
Science and technology project of Xianyang city
Subject
General Earth and Planetary Sciences
Reference43 articles.
1. Realizing Target Detection in SAR Images Based on Multiscale Superpixel Fusion;Lin;Sensors,2021 2. Wang, Z., Wang, S., Xu, C., Li, C., Yue, B., and Liang, X. (2017, January 23–28). SAR Images Super-resolution via Cartoon-texture Image Decomposition and Jointly Optimized Regressors. Proceedings of the 2017 International Geoscience and Remote Sensing Symposium, Fort Worth, TX, USA. 3. Kong, L., and Xu, X. (2019). A MIMO-SAR Tomography Algorithm Based on Fully-Polarimetric Data. Sensors, 19. 4. Greenspan, M., Pham, L., and Tardella, N. (1998, January 14). Development and evaluation of a real time SAR ATR system. Proceedings of the 1998 IEEE Radar Conference, RADARCON’98, Challenges in Radar Systems and Solutions, Dallas, TX, USA. Cat. No. 98CH36197. 5. Comparison and fusion of co-occurrence, Gabor and MRF texture features for classification of SAR sea-ice imagery;Clausi;Atmos.-Ocean,2001
|
|