Semi-Supervised SAR ATR Framework with Transductive Auxiliary Segmentation

TL;DR

This paper introduces a semi-supervised SAR ATR framework that leverages auxiliary segmentation and transductive learning to improve recognition accuracy with limited labeled data, demonstrated on the MSTAR dataset.

Contribution

The novel framework combines auxiliary segmentation and transductive learning to enhance SAR ATR performance with few labeled samples.

Findings

Achieves 94.18% recognition accuracy with 20 training samples per class.

Recognition ratios exceed 88% with only 10 samples per class under EOCs.

Effective in few-shot learning scenarios on the MSTAR dataset.

Abstract

Convolutional neural networks (CNNs) have achieved high performance in synthetic aperture radar (SAR) automatic target recognition (ATR). However, the performance of CNNs depends heavily on a large amount of training data. The insufficiency of labeled training SAR images limits the recognition performance and even invalidates some ATR methods. Furthermore, under few labeled training data, many existing CNNs are even ineffective. To address these challenges, we propose a Semi-supervised SAR ATR Framework with transductive Auxiliary Segmentation (SFAS). The proposed framework focuses on exploiting the transductive generalization on available unlabeled samples with an auxiliary loss serving as a regularizer. Through auxiliary segmentation of unlabeled SAR samples and information residue loss (IRL) in training, the framework can employ the proposed training loop process and gradually exploit the information compilation of recognition and segmentation to construct a helpful inductive bias and achieve high performance. Experiments conducted on the MSTAR dataset have shown the effectiveness of our proposed SFAS for few-shot learning. The recognition performance of 94.18\% can be achieved under 20 training samples in each class with simultaneous accurate segmentation results. Facing variances of EOCs, the recognition ratios are higher than 88.00\% when 10 training samples each class.