# DualBranch-AMR: A Semi-Supervised AMR Method Based on Dual-Student Consistency Regularization with Dynamic Stability Evaluation

## TL;DR

This paper introduces DualBranch-AMR, a semi-supervised method for automatic modulation recognition that uses unlabeled data effectively and achieves high accuracy with minimal labeled data.

## Contribution

A novel semi-supervised AMR method using dual-student consistency regularization and dynamic stability evaluation for pseudo-labels.

## Key findings

- DualBranch-AMR outperforms traditional supervised methods on benchmark datasets.
- With only 5% labeled data, it achieves 55.84% recognition accuracy.
- The method reaches over 90% of fully supervised performance.

## Abstract

Modulation recognition, as one of the key technologies in the field of wireless communications, holds significant importance in applications such as spectrum resource management, interference suppression, and cognitive radio. While deep learning has substantially improved the performance of Automatic Modulation Recognition (AMR), it heavily relies on large amounts of labeled data. Given the high annotation costs and privacy concerns, researching semi-supervised AMR methods that leverage readily available unlabeled data for training is of great significance. This study constructs a semi-supervised AMR method based on dual-student. Specifically, we first adopt a dual-branch co-training architecture to fully exploit unlabeled data and effectively learn deep feature representations. Then, we develop a dynamic stability evaluation module using strong and weak augmentation strategies to improve the accuracy of generated pseudo-labels. Finally, based on the dual-student semi-supervised framework and pseudo-label stability evaluation, we propose a stability-guided consistency regularization constraint method and conduct semi-supervised AMR model training. The experimental results demonstrate that the proposed DualBranch-AMR method significantly outperforms traditional supervised baseline approaches on benchmark datasets. With only 5% labeled data, it achieves a recognition accuracy of 55.84%, reaching over 90% of the performance of fully supervised training. This validates the superiority of the proposed method under semi-supervised conditions.