Semisupervised Specific Emitter Identification Based on Contrastive Learning and Data Augmentation

Abstract

In recent years, with the development of deep learning (DL), DL-based specific emitter identification (SEI) has outperformed the traditional methods in accuracy. However, DL-based methods often depend on huge labeled samples for training, which are not available in certain situations. Semisupervised methods can be trained with a large number of unlabeled samples and few labeled samples, thereby reducing the need for manual labeling signals. In this article, a semisupervised SEI method based on contrastive learning and data augmentation, semisupervised multiple positive contrastive learning SEI (SSMPCL-SEI), is proposed. SSMPCL-SEI modifies the self-supervised contrastive learning to cope with multiple positive samples and learns category information from both labeled and unlabeled samples. Furthermore, data augmentation for the classifier is used after pretraining to improve the classification ability. The experimental results with an drone dataset and an automatic dependent surveillance-broadcast dataset show that SSMPCL-SEI yields better identification performance than other state-of-the-art semisupervised SEI methods.