Few-Shot Recognition of Multifunction Radar Modes via Refined Prototypical Random Walk Network

Multifunctional radars (MFRs) can generate a variety of working modes for different tasks based on flexible modulation types and programmable parameters. The neural network has been widely used to recognize these fine-grained MFR modes. However, it requires a large number of samples with expert annotation in advance, which is hardly available in practical applications. Therefore, a few-shot learning method is used to learn "general information" and transfer it into new tasks where only a small number of labeled samples are provided. In order to improve its effect, unlabeled samples are utilized to provide "manifold information" that describes the distribution among data. This article proposes a framework of coding refined prototypical random walk network combining these two kinds of information. The whole framework is divided into three modules, i.e., preprocessing module, embedding module, and refined prototypical random walk module, which are, respectively, used to enhance the signal expression to adapt to nonideal situations, extract distinguishable features to compute prototypes, and utilize "manifold information" for better classification. The experimental results and analysis show that the proposed method achieves excellent performance for MFR fine-grained mode recognition even under the condition of a small number of samples. In addition, the robustness of the proposed method is verified under the influence of different nonideal factors.