.png){kind=icon}
.png){kind=icon}
Return
An Efficient Model for Few-Shot Automatic Modulation Recognition Based on Supervised Contrastive Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TVT.2024.3483204.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The application of deep learning (DL) has improved the reliability and intelligence of automatic modulation recognition (AMR). However, real-world scenarios often involve a limited number of signal samples. Furthermore, most existing DL-based AMR models improve performance at the cost of computational complexity. Therefore, we propose an efficient contrastive multi-stage sparse attention network (CMSSAN) model for few-shot AMR without auxiliary datasets. Specifically, supervised contrastive learning is utilized to enhance the feature representation of the signal, and a joint loss with dynamic weights is constructed to balance the representation and classification tasks. In addition, a lightweight MSSAN encoder is proposed to enhance the recognition performance with lower computations and parameters. Simulation experiments are conducted on the ablation experiment and hyperparameter analysis of the proposed model, and the superiority of the model is verified on several datasets.
Keywords:
Feature extraction
Convolution
Transformers
Training
Vectors
Computational modeling
Accuracy
Modulation
Encoding
Kernel
Automatic modulation recognition
Few-shot
Lightweight
Contrastive Learning
Transformer network
Journal
IF:
7.1
Papers:
1.8W
Citations:
6.6W