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

Xiaowei Hu,Yiduo Guo,Weike Feng,Qiang Wang

doi:10.3390/rs13183554

Xiaowei Hu, Yiduo Guo + Show 2 more

Open Access

https://doi.org/10.3390/rs13183554

Copy DOI

Abstract

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.

Highlights

Automatic target recognition (ATR) is a challenging task for synthetic aperture radar (SAR) [1,2]
We focus on the problem of Open set recognition (OSR) in SAR-ATR where there is no information about the unknown classes, including the training samples, class number, semantic information, etc
The main objective in this paper is to find an explicable feature space, in which the attributes of the SAR images can be well represented and the unknown classes can be distinguished

Summary

Introduction

Automatic target recognition (ATR) is a challenging task for synthetic aperture radar (SAR) [1,2]. Different from the traditional technologies which extract the image features manually, the deep learning (DL) technology can automatically extract the image features by combining the feature extractor and the classifier, so the remarkable performance on target recognition can be achieved. Several results on some public data sets for SAR-ATR by using DL (deep learning) have been reported and are far beyond the results by using traditional technologies [11,12,13]. Most of the existing SAR target recognition methods suppose that the target classes in the test set have appeared in the training set. The traditional SAR-ATR methods will not work or deteriorate seriously for the unknown classes

Methods

Results

Discussion

Conclusion