Feature Learning for SAR Target Recognition with Unknown Classes by Using CVAE-GAN

Remote Sensing

Yiduo Guo¹  Weike Feng¹  Qiang Wang²  Xiaowei Hu³ 

[1] Early Warning and Detection Department, Air Force Engineering University, Xi’an 710051, China;Experimental Training Base of College of Information and Communication, National University of Defense Technology, Xi’an 710106, China;Key Lab for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, China;

关键词: feature learning;    SAR-ATR;    unknown classes;    deep learning;    CVAE-GAN;   

DOI  :  10.3390/rs13183554

来源: DOAJ

【 摘 要 】

Even though deep learning (DL) has achieved excellent results on some public data sets for synthetic aperture radar (SAR) automatic target recognition(ATR), several problems exist at present. One is the lack of transparency and interpretability for most of the existing DL networks. Another is the neglect of unknown target classes which are often present in practice. To solve the above problems, a deep generation as well as recognition model is derived based on Conditional Variational Auto-encoder (CVAE) and Generative Adversarial Network (GAN). A feature space for SAR-ATR is built based on the proposed CVAE-GAN model. By using the feature space, clear SAR images can be generated with given class labels and observation angles. Besides, the feature of the SAR image is continuous in the feature space and can represent some attributes of the target. Furthermore, it is possible to classify the known classes and reject the unknown target classes by using the feature space. Experiments on the MSTAR data set validate the advantages of the proposed method.

【 授权许可】

Unknown