DyCo-CL reports a 6.27% accuracy improvement in 1-shot AMR on RML benchmarks via geometry-aware contrastive learning, VAA, semantic consistency, a Signal-Adaptive Swin Backbone, and Hybrid Knowledge Fusion.
Since M is a fixed constant (e.g., M= 16) andM≪L,C M is independent ofL
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition
DyCo-CL reports a 6.27% accuracy improvement in 1-shot AMR on RML benchmarks via geometry-aware contrastive learning, VAA, semantic consistency, a Signal-Adaptive Swin Backbone, and Hybrid Knowledge Fusion.