通过脉冲时序位置关系提升雷达信号跨模式识别能力
Position-Aware Self-supervised Representation Learning for Cross-mode Radar Signal Recognition
- 利用脉冲级时间动态建模位置关系，无需复杂增强或掩码
- 在长尾设置下实现更强的判别力与鲁棒性
- 适合实际电磁环境中的雷达信号识别任务
开放电磁环境中雷达信号识别面临工作模式多样和未见雷达类型等挑战。现有方法常忽略脉冲序列中的位置关系，难以捕捉长期语义依赖。我们提出RadarPos，一种位置感知的自监督框架，利用脉冲级时间动态建模，无需复杂数据增强或掩码操作，相比对比学习或掩码重建方法，在位置关系建模上表现更优。基于该框架，我们在长尾设置下评估跨模式雷达信号识别性能，实验表明其具备更强的判别能力和鲁棒性，展现出在真实电磁环境中的实用价值。
原文摘要 · Abstract (English)
Radar signal recognition in open electromagnetic environments is challenging due to diverse operating modes and unseen radar types. Existing methods often overlook position relations in pulse sequences, limiting their ability to capture semantic dependencies over time. We propose RadarPos, a position-aware self-supervised framework that leverages pulse-level temporal dynamics without complex augmentations or masking, providing improved position relation modeling over contrastive learning or masked reconstruction. Using this framework, we evaluate cross-mode radar signal recognition under the long-tailed setting to assess adaptability and generalization. Experimental results demonstrate enhanced discriminability and robustness, highlighting practical applicability in real-world electromagnetic environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。