A Semi-Supervised Synthetic Aperture Radar (SAR) Image Recognition Algorithm Based on an Attention Mechanism and Bias-Variance Decomposition

Fei Gao,Wei Shi,Jun Wang,Amir Hussain,Huiyu Zhou

doi:10.1109/access.2019.2933459

Abstract

Synthetic Aperture Radar (SAR) target recognition is an important research direction of SAR image interpretation. In recent years, most of machine learning methods applied to SAR target recognition are supervised learning which requires a large number of labeled SAR images. However, labeling SAR images is expensive and time-consuming. We hereby propose an end-to-end semi-supervised recognition method based on an attention mechanism and bias-variance decomposition, which focuses on the unlabeled data screening and pseudo-labels assignment. Different from other learning methods, the training set in each iteration is determined by a module that we here propose, called dataset attention module (DAM). Through DAM, the contributing unlabeled data will have more possibilities to be added into the training set, while the non-contributing and hard-to-learn unlabeled data will receive less attention. During the training process, each unlabeled data will be input into the network for prediction. The pseudo-label of the unlabeled data is considered to be the most probable classification in the multiple predictions, which reduces the risk of the single prediction. We calculate the prediction bias-and-variance of all the unlabeled data and use the result as the criteria to screen the unlabeled data in DAM. In this paper, we carry out semi-supervised learning experiments under different unlabeled rates on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset. The recognition accuracy of our method is better than several state of the art semi-supervised learning algorithms.

Highlights

Synthetic Aperture Radar (SAR) has the ability to capture the images of the earth’s surface in most weather conditions from a long distance
The main contributions made in this paper are follows: Firstly, we propose a new attention mechanism by combining the attention mechanism and semi-supervised learning, namely dataset attention module (DAM)
According to the results of the evaluation, unlabeled data will be screened by a module that we propose, called dataset attention module (DAM)

Summary

Introduction

SAR has the ability to capture the images of the earth’s surface in most weather conditions from a long distance. The associate editor coordinating the review of this manuscript and approving it for publication was Nilanjan Dey. several years. The method of SAR target recognition includes template matching [1], [2], model-based methods [3]–[5] and machine learning [6]–[13]. Template matching needs to store plenty of templates and model-based methods need to deal with the problems in feature extraction. Traditional machine learning methods require complex preprocessing SAR images, including denoising and feature extraction. SAR images are sensitive to the change of target azimuth and orientation, which cause many problems to the traditional SAR target recognition methods.

Methods

Findings

Discussion

Conclusion