Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition
For researchers in automatic modulation recognition, this work provides a geometry-aware contrastive learning framework that enhances few-shot performance.
DyCo-CL improves few-shot automatic modulation recognition by 6.27% accuracy in 1-shot settings over prior methods, addressing issues of isotropic augmentations and spectral instability.
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.