Crucial Feature Capture and Discrimination for Limited Training Data SAR ATR

TL;DR

This paper introduces a SAR ATR framework designed for limited training data, focusing on capturing and discriminating crucial image features through a dual-branch structure and dynamic feature weighting.

Contribution

The proposed method uniquely combines global and local feature extraction with modules that automatically identify and utilize key image regions for improved recognition with limited data.

Findings

Improves recognition accuracy on MSTAR and OPENSAR datasets.

Enhances feature distribution and recognition probability.

Outperforms existing methods in limited data scenarios.

Abstract

Although deep learning-based methods have achieved excellent performance on SAR ATR, the fact that it is difficult to acquire and label a lot of SAR images makes these methods, which originally performed well, perform weakly. This may be because most of them consider the whole target images as input, but the researches find that, under limited training data, the deep learning model can't capture discriminative image regions in the whole images, rather focus on more useless even harmful image regions for recognition. Therefore, the results are not satisfactory. In this paper, we design a SAR ATR framework under limited training samples, which mainly consists of two branches and two modules, global assisted branch and local enhanced branch, feature capture module and feature discrimination module. In every training process, the global assisted branch first finishes the initial recognition based on the whole image. Based on the initial recognition results, the feature capture module automatically searches and locks the crucial image regions for correct recognition, which we named as the golden key of image. Then the local extract the local features from the captured crucial image regions. Finally, the overall features and local features are input into the classifier and dynamically weighted using the learnable voting parameters to collaboratively complete the final recognition under limited training samples. The model soundness experiments demonstrate the effectiveness of our method through the improvement of feature distribution and recognition probability. The experimental results and comparisons on MSTAR and OPENSAR show that our method has achieved superior recognition performance.