提出几何感知对比学习框架，提升少样本调制识别准确率
Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition
- 用动态一致性对比学习融合虚拟对抗增强与语义一致性损失
- 在1样本设置下相比现有方法提升6.27%识别准确率
- 适合对少样本通信信号分类有需求的研究者
标准自监督学习在自动调制识别中面临无效的各向同性增强、频谱不稳定性与语义漂移问题。为此，我们提出动态一致性对比学习（DyCo-CL），一种几何感知框架，将虚拟对抗增强（VAA）与语义一致性损失结合。理论分析表明，该策略对编码器起到隐式频谱正则化作用，实现稳定的流形探索。同时，基于固定窗口注意力的信号自适应Swin主干网络提升了结构稳定性，混合知识融合模块则引入物理先验锚定表征。在RML基准上的实验表明，DyCo-CL在1样本设置下相比先前方法取得6.27%的准确率提升。
原文摘要 · Abstract (English)
Standard Self-Supervised Learning (SSL) for Automatic Modulation Recognition (AMR) struggles with ineffective isotropic augmentations, spectral instability, and semantic drift. To address these challenges, we propose Dynamic-Consistency Contrastive Learning (DyCo-CL), a geometry-aware framework that couples Virtual Adversarial Augmentation (VAA) with a semantic consistency loss. We provide a theoretical analysis indicating that this strategy acts as an implicit spectral regularizer for the encoder, enabling stable manifold exploration. Complementing this, our Signal-Adaptive Swin Backbone with fixed-window attention improves structural stability by constraining attention locality, while a Hybrid Knowledge Fusion module anchors representations with physical priors. Experiments on RML benchmarks show that DyCo-CL achieves a 6.27% accuracy gain in 1-shot settings over prior methods.
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。