Cross-Domain Knowledge Transfer for Underwater Acoustic Classification Using Pre-trained Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909540171120640 |
|---|---|
| author | Mohammadi, Amirmohammad Kelhe, Tejashri Carreiro, Davelle Van Dine, Alexandra Peeples, Joshua |
| author_facet | Mohammadi, Amirmohammad Kelhe, Tejashri Carreiro, Davelle Van Dine, Alexandra Peeples, Joshua |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13878 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cross-Domain Knowledge Transfer for Underwater Acoustic Classification Using Pre-trained Models Mohammadi, Amirmohammad Kelhe, Tejashri Carreiro, Davelle Van Dine, Alexandra Peeples, Joshua Sound Machine Learning Audio and Speech Processing 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. |
| title | Cross-Domain Knowledge Transfer for Underwater Acoustic Classification Using Pre-trained Models |
| topic | Sound Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2409.13878 |