Meta Supervised Contrastive Learning for Few-Shot Open-Set Modulation Classification With Signal Constellation

Jikui Zhao, Huaxia Wang, Shengliang Peng, Yu Dong Yao

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

In this work, we introduce a method for few-shot open-set modulation classification utilizing signal constellation diagrams, based on a Meta Supervised Contrastive Learning (MSCL) algorithm. MSCL combines the strengths of supervised contrastive learning and meta-learning to effectively amplify inter-class distinctions and reinforce intra-class compactness. The experimental results demonstrate that MSCL exhibits superior performance in both few-shot and open-set Automatic Modulation Classification (AMC) recognition. Code available at: https://github.com/jikuizhao/MSCL

Original languageEnglish
Pages (from-to)837-841
Number of pages5
JournalIEEE Communications Letters
Volume28
Issue number4
DOIs
StatePublished - 1 Apr 2024

Keywords

  • Few-shot learning
  • meta-learning
  • modulation classification
  • open-set classification
  • signal constellation

Fingerprint

Dive into the research topics of 'Meta Supervised Contrastive Learning for Few-Shot Open-Set Modulation Classification With Signal Constellation'. Together they form a unique fingerprint.

Cite this