Robust SAR Automatic Target Recognition Based on Transferred MS-CNN with L2-Regularization
Joint Authors
Zhai, Yikui
Deng, Wenbo
Gan, Junying
Piuri, Vincenzo
Zeng, Junying
Xu, Ying
Ke, Qirui
Sun, Bing
Source
Computational Intelligence and Neuroscience
Issue
Vol. 2019, Issue 2019 (31 Dec. 2019), pp.1-13, 13 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2019-11-15
Country of Publication
Egypt
No. of Pages
13
Main Subjects
Abstract EN
Though Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) via Convolutional Neural Networks (CNNs) has made huge progress toward deep learning, some key issues still remain unsolved due to the lack of sufficient samples and robust model.
In this paper, we proposed an efficient transferred Max-Slice CNN (MS-CNN) with L2-Regularization for SAR ATR, which could enrich the features and recognize the targets with superior performance.
Firstly, the data amplification method is presented to reduce the computational time and enrich the raw features of SAR targets.
Secondly, the proposed MS-CNN framework with L2-Regularization is trained to extract robust features, in which the L2-Regularization is incorporated to avoid the overfitting phenomenon and further optimizing our proposed model.
Thirdly, transfer learning is introduced to enhance the feature representation and discrimination, which could boost the performance and robustness of the proposed model on small samples.
Finally, various activation functions and dropout strategies are evaluated for further improving recognition performance.
Extensive experiments demonstrated that our proposed method could not only outperform other state-of-the-art methods on the public and extended MSTAR dataset but also obtain good performance on the random small datasets.
American Psychological Association (APA)
Zhai, Yikui& Deng, Wenbo& Xu, Ying& Ke, Qirui& Gan, Junying& Sun, Bing…[et al.]. 2019. Robust SAR Automatic Target Recognition Based on Transferred MS-CNN with L2-Regularization. Computational Intelligence and Neuroscience،Vol. 2019, no. 2019, pp.1-13.
https://search.emarefa.net/detail/BIM-1129652
Modern Language Association (MLA)
Zhai, Yikui…[et al.]. Robust SAR Automatic Target Recognition Based on Transferred MS-CNN with L2-Regularization. Computational Intelligence and Neuroscience No. 2019 (2019), pp.1-13.
https://search.emarefa.net/detail/BIM-1129652
American Medical Association (AMA)
Zhai, Yikui& Deng, Wenbo& Xu, Ying& Ke, Qirui& Gan, Junying& Sun, Bing…[et al.]. Robust SAR Automatic Target Recognition Based on Transferred MS-CNN with L2-Regularization. Computational Intelligence and Neuroscience. 2019. Vol. 2019, no. 2019, pp.1-13.
https://search.emarefa.net/detail/BIM-1129652
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1129652