SAR ATR Method with Limited Training Data via an Embedded Feature Augmenter and Dynamic Hierarchical-Feature Refiner

TL;DR

This paper introduces a novel SAR ATR method that enhances feature diversity and discriminability using an embedded feature augmenter and a dynamic hierarchical-feature refiner, significantly improving recognition accuracy with limited training data.

Contribution

It proposes a new approach combining feature augmentation and local feature refinement to boost SAR ATR performance under data scarcity conditions.

Findings

Achieved superior accuracy on MSTAR, OpenSARShip, and FUSAR-Ship datasets.

Demonstrated robustness and effectiveness with limited training data.

Enhanced feature separability and class discrimination.

Abstract

Without sufficient data, the quantity of information available for supervised training is constrained, as obtaining sufficient synthetic aperture radar (SAR) training data in practice is frequently challenging. Therefore, current SAR automatic target recognition (ATR) algorithms perform poorly with limited training data availability, resulting in a critical need to increase SAR ATR performance. In this study, a new method to improve SAR ATR when training data are limited is proposed. First, an embedded feature augmenter is designed to enhance the extracted virtual features located far away from the class center. Based on the relative distribution of the features, the algorithm pulls the corresponding virtual features with different strengths toward the corresponding class center. The designed augmenter increases the amount of information available for supervised training and improves the separability of the extracted features. Second, a dynamic hierarchical-feature refiner is proposed to capture the discriminative local features of the samples. Through dynamically generated kernels, the proposed refiner integrates the discriminative local features of different dimensions into the global features, further enhancing the inner-class compactness and inter-class separability of the extracted features. The proposed method not only increases the amount of information available for supervised training but also extracts the discriminative features from the samples, resulting in superior ATR performance in problems with limited SAR training data. Experimental results on the moving and stationary target acquisition and recognition (MSTAR), OpenSARShip, and FUSAR-Ship benchmark datasets demonstrate the robustness and outstanding ATR performance of the proposed method in response to limited SAR training data.