Self-Supervised Learning-For Underwater Acoustic Signal Classification With Mixup

Underwater acoustic signal classification is a critical task that involves identifying different types of signals in a complex and dynamic underwater environment, which is often contaminated by strong ambient noise. Recent studies have demonstrated that deep learning-based methods can achieve remarkable performance in this task by leveraging large-scale labeled data. However, obtaining labeled data in real-world scenarios can be challenging due to the labor-intensive and expert-dependent nature of the labeling process, especially for underwater scenarios. In this study, we propose a novel self-supervised learning framework combined with mixup-based augmentation that can learn discriminative representations from large-scale unlabeled data, thereby reducing the dependence on labeled data. In addition, we propose a test time augmentation module to further improve the model's robustness. Our proposed approach achieves a classification accuracy of 86.33% on the DeepShip dataset, surpassing previous competitive methods by a significant margin. Notably, our method demonstrates excellent generalization performance in few-shot scenarios and low signal-to-noise settings, highlighting its potential for practical applications.