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.
Publication date: June 2025
Link: https://arxiv.org/abs/2409.13878
Citation: A. Mohammadi, T. Kelhe, D. Carreiro, A. V. Dine, and J. Peeples, “Cross-Domain Knowledge Transfer for Underwater Acoustic Classification Using Pre-trained Models,” in IEEE OCEANS, 2025, in Press. doi: arXiv: 2409.13878.