雷达科学与技术2026，Vol.24Issue(1)：74-82,93,10.DOI:10.3969/j.issn.1672-2337.2026.01.008
基于多尺度特征匹配的小样本雷达无人机识别
Few-Shot Radar UAV Recognition Based on Multi-Scale Feature Matching
摘要
Abstract
In order to improve the classification accuracy of radar-based UAV signals under limited data condi-tions,this paper proposes a few-shot classification framework EMLNet(EfficientNet-based Multi-scale Learning Net-work)based on multi-scale feature enhancement and metric learning.The method integrates an efficient multi-scale at-tention mechanism(EMA)into the lightweight EfficientNet backbone for feature extraction,which effectively enhances the stability and discriminative ability of features through multi-scale parallel sub-network with cross-spatial depen-dence modeling.In the classification stage,a local feature matching strategy is adopted to achieve fine-grained similarity modeling between the support set and the query set.To further improve training stability and generalization perfor-mance,a composite loss function(PCE Loss)that combines prototypical loss and cross-entropy loss is introduced to op-timize inter-class discrimination while maintaining intra-class feature aggregation.Experiments are carried out on the open-source Doppler radar dataset.The experimental results demonstrate that the proposed method achieves significant performance advantages in few-shot learning scenarios.关键词
无人机分类/连续波雷达/小样本学习/EfficientNet网络/度量学习/时频图Key words
UAV classification/continuous wave radar/few-shot learning/EfficientNet/metric learning/time-frequency map分类
信息技术与安全科学引用本文复制引用
孙延鹏,石增辉,屈乐乐..基于多尺度特征匹配的小样本雷达无人机识别[J].雷达科学与技术,2026,24(1):74-82,93,10.基金项目
国家自然科学基金(61671310) （61671310）
航空科学基金(2019ZC054004) （2019ZC054004）
辽宁省高校基本科研业务费(LJ222410143071) （LJ222410143071）
