SAR-BagNet: An Ante-hoc Interpretable Recognition Model Based on Deep Network for SAR Image
Convolutional neural networks (CNNs) have been widely used in SAR image recognition and have achieved high recognition accuracy on some public datasets. However, due to the opacity of the decision-making mechanism, the reliability and credibility of CNNs are insufficient at present, which hinders th...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/9/2150 |
| _version_ | 1797503047664926720 |
|---|---|
| author | Peng Li Cunqian Feng Xiaowei Hu Zixiang Tang |
| author_facet | Peng Li Cunqian Feng Xiaowei Hu Zixiang Tang |
| author_sort | Peng Li |
| collection | DOAJ |
| description | Convolutional neural networks (CNNs) have been widely used in SAR image recognition and have achieved high recognition accuracy on some public datasets. However, due to the opacity of the decision-making mechanism, the reliability and credibility of CNNs are insufficient at present, which hinders their application in some important fields such as SAR image recognition. In recent years, various interpretable network structures have been proposed to discern the relationship between a CNN’s decision and image regions. Unfortunately, most interpretable networks are based on optical images, which have poor recognition performance for SAR images, and most of them cannot accurately explain the relationship between image parts and classification decisions. Based on the above problems, in this study, we present SAR-BagNet, which is a novel interpretable recognition framework for SAR images. SAR-BagNet can provide a clear heatmap that can accurately reflect the impact of each part of a SAR image on the final network decision. Except for the good interpretability, SAR-BagNet also has high recognition accuracy and can achieve 98.25% test accuracy. |
| first_indexed | 2024-03-10T03:44:55Z |
| format | Article |
| id | doaj.art-69fc31f8238f495fa0ca099051e5f7ed |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T03:44:55Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-69fc31f8238f495fa0ca099051e5f7ed2023-11-23T09:11:22ZengMDPI AGRemote Sensing2072-42922022-04-01149215010.3390/rs14092150SAR-BagNet: An Ante-hoc Interpretable Recognition Model Based on Deep Network for SAR ImagePeng Li0Cunqian Feng1Xiaowei Hu2Zixiang Tang3Early Warning and Detection Department, Air Force Engineering University, Xi’an 710051, ChinaEarly Warning and Detection Department, Air Force Engineering University, Xi’an 710051, ChinaEarly Warning and Detection Department, Air Force Engineering University, Xi’an 710051, ChinaEarly Warning and Detection Department, Air Force Engineering University, Xi’an 710051, ChinaConvolutional neural networks (CNNs) have been widely used in SAR image recognition and have achieved high recognition accuracy on some public datasets. However, due to the opacity of the decision-making mechanism, the reliability and credibility of CNNs are insufficient at present, which hinders their application in some important fields such as SAR image recognition. In recent years, various interpretable network structures have been proposed to discern the relationship between a CNN’s decision and image regions. Unfortunately, most interpretable networks are based on optical images, which have poor recognition performance for SAR images, and most of them cannot accurately explain the relationship between image parts and classification decisions. Based on the above problems, in this study, we present SAR-BagNet, which is a novel interpretable recognition framework for SAR images. SAR-BagNet can provide a clear heatmap that can accurately reflect the impact of each part of a SAR image on the final network decision. Except for the good interpretability, SAR-BagNet also has high recognition accuracy and can achieve 98.25% test accuracy.https://www.mdpi.com/2072-4292/14/9/2150deep learningtarget recognitioninterpretable networksynthetic aperture radar (SAR) image interpretation |
| spellingShingle | Peng Li Cunqian Feng Xiaowei Hu Zixiang Tang SAR-BagNet: An Ante-hoc Interpretable Recognition Model Based on Deep Network for SAR Image Remote Sensing deep learning target recognition interpretable network synthetic aperture radar (SAR) image interpretation |
| title | SAR-BagNet: An Ante-hoc Interpretable Recognition Model Based on Deep Network for SAR Image |
| title_full | SAR-BagNet: An Ante-hoc Interpretable Recognition Model Based on Deep Network for SAR Image |
| title_fullStr | SAR-BagNet: An Ante-hoc Interpretable Recognition Model Based on Deep Network for SAR Image |
| title_full_unstemmed | SAR-BagNet: An Ante-hoc Interpretable Recognition Model Based on Deep Network for SAR Image |
| title_short | SAR-BagNet: An Ante-hoc Interpretable Recognition Model Based on Deep Network for SAR Image |
| title_sort | sar bagnet an ante hoc interpretable recognition model based on deep network for sar image |
| topic | deep learning target recognition interpretable network synthetic aperture radar (SAR) image interpretation |
| url | https://www.mdpi.com/2072-4292/14/9/2150 |
| work_keys_str_mv | AT pengli sarbagnetanantehocinterpretablerecognitionmodelbasedondeepnetworkforsarimage AT cunqianfeng sarbagnetanantehocinterpretablerecognitionmodelbasedondeepnetworkforsarimage AT xiaoweihu sarbagnetanantehocinterpretablerecognitionmodelbasedondeepnetworkforsarimage AT zixiangtang sarbagnetanantehocinterpretablerecognitionmodelbasedondeepnetworkforsarimage |