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.

Radio signal recognition is a crucial function in electronic warfare. Precise identification and localisation of radar pulse activities are required by electronic warfare systems to produce effective countermeasures. Despite the importance of these tasks, deep learning-based radar pulse activity recognition methods have remained largely underexplored. While deep learning for radar modulation recognition has been explored previously, classification tasks are generally limited to short and non-interleaved IQ signals, limiting their applicability to military applications. To address this gap, we introduce an end-to-end multi-stage learning approach to detect and localise pulse activities of interleaved radar signals across an extended time horizon. We propose a simple, yet highly effective multi-stage architecture for incrementally predicting fine-grained segmentation masks that localise radar pulse activities across multiple channels. We demonstrate the performance of our approach against several reference models on a novel radar dataset, while also providing a first-of-its-kind benchmark for radar pulse activity segmentation.

Radio signal recognition is a crucial task in both civilian and The application of convolutional neural networks (CNNs) military applications, as accurate and timely identification of to automatic modulation classification (AMC) was introduced unknown signals is an essential part of spectrum management by [8]. Their early works [9, 10] together with the release and electronic warfare. The majority of research in this field of several public datasets [11] initiated a wave of interest in has focused on applying deep learning for modulation classification, DL-based RSR. Recently, several alternative DL approaches leaving the task of signal characterisation as an understudied that adopt recurrent neural networks (RNNs) and hybrid architectures area. This paper addresses this gap by presenting [12] were able to consistently achieve above 90% an approach for tackling radar signal classification and characterisation modulation classification accuracy in relatively high signalto-noise as a multi-task learning (MTL) problem. We propose ratio (SNR) settings. Despite the success of DNNs, the IQ Signal Transformer (IQST) among several reference many recent approaches still rely on handcrafted features to architectures that allow for simultaneous optimisation of pre-process the complex-valued, in-phase and quadrature (IQ) multiple regression and classification tasks. We demonstrate data into image-based representations, such as spectrograms the performance of our proposed MTL model on a synthetic [12], prior to training. These approaches effectively transform radar dataset, while also providing a first-of-its-kind benchmark RSR into an image classification problem, and thus limits the for radar signal characterisation.