English

Cross-Domain Knowledge Transfer for Underwater Acoustic Classification Using Pre-trained Models

Sound 2025-03-19 v2 Machine Learning Audio and Speech Processing

Abstract

Transfer learning is commonly employed to leverage large, pre-trained models and perform fine-tuning for downstream tasks. The most prevalent pre-trained models are initially trained using ImageNet. However, their ability to generalize can vary across different data modalities. This study compares pre-trained Audio Neural Networks (PANNs) and ImageNet pre-trained models within the context of underwater acoustic target recognition (UATR). It was observed that the ImageNet pre-trained models slightly out-perform pre-trained audio models in passive sonar classification. We also analyzed the impact of audio sampling rates for model pre-training and fine-tuning. This study contributes to transfer learning applications of UATR, illustrating the potential of pre-trained models to address limitations caused by scarce, labeled data in the UATR domain.

Keywords

Cite

@article{arxiv.2409.13878,
  title  = {Cross-Domain Knowledge Transfer for Underwater Acoustic Classification Using Pre-trained Models},
  author = {Amirmohammad Mohammadi and Tejashri Kelhe and Davelle Carreiro and Alexandra Van Dine and Joshua Peeples},
  journal= {arXiv preprint arXiv:2409.13878},
  year   = {2025}
}

Comments

6 pages, 4 figures, This work has been submitted to the IEEE for possible publication. Added Grad-CAM analysis. Title changed. This work has been accepted to IEEE OCEANS 2025

R2 v1 2026-06-28T18:51:58.173Z