Radar Signal Recognition through Self-Supervised Learning and Domain Adaptation

2025-01-07

AI Summary

To address the severe scarcity of labeled radar signal data in electronic warfare, this paper proposes a self-supervised pretraining and radio-frequency (RF) domain transfer framework based on masked signal modeling. We pioneer the application of Masked Autoencoders (MAEs) to self-supervised pretraining of baseband I/Q signals and achieve cross-RF-domain representation transfer (from communication to radar). We further introduce the first few-shot radar signal recognition benchmark. Our method integrates a lightweight ResNet architecture with I/Q-signal-specific modeling and domain-adaptive fine-tuning strategies. Experimental results demonstrate that, under the 1-shot setting, our approach improves classification accuracy by 17.5% over a non-self-supervised baseline with in-domain pretraining, and by 16.31% with cross-domain pretraining—substantially enhancing few-shot generalization capability for radar signal recognition.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Automatic radar signal recognition (RSR) plays a pivotal role in electronic warfare (EW), as accurately classifying radar signals is critical for informing decision-making processes. Recent advances in deep learning have shown significant potential in improving RSR performance in domains with ample annotated data. However, these methods fall short in EW scenarios where annotated RF data are scarce or impractical to obtain. To address these challenges, we introduce a self-supervised learning (SSL) method which utilises masked signal modelling and RF domain adaption to enhance RSR performance in environments with limited RF samples and labels. Specifically, we investigate pre-training masked autoencoders (MAE) on baseband in-phase and quadrature (I/Q) signals from various RF domains and subsequently transfer the learned representation to the radar domain, where annotated data are limited. Empirical results show that our lightweight self-supervised ResNet model with domain adaptation achieves up to a 17.5% improvement in 1-shot classification accuracy when pre-trained on in-domain signals (i.e., radar signals) and up to a 16.31% improvement when pre-trained on out-of-domain signals (i.e., comm signals), compared to its baseline without SSL. We also provide reference results for several MAE designs and pre-training strategies, establishing a new benchmark for few-shot radar signal classification.

Problem

• Electronic Warfare
• Radar Signal Recognition
• Limited Data

Innovation

• Self-learning Method
• Signal Pattern Recognition
• Adaptive RF Environment