Guardado en:
Detalles Bibliográficos
Autores principales: Park, Sangwon, Kim, Dongjun, Byun, Sung-Hoon, Park, Sangwook
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2601.13679
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909995606474752
author Park, Sangwon
Kim, Dongjun
Byun, Sung-Hoon
Park, Sangwook
author_facet Park, Sangwon
Kim, Dongjun
Byun, Sung-Hoon
Park, Sangwook
contents This letter presents ShuffleFAC, a lightweight acoustic model for ship-radiated sound classification in resource-constrained maritime monitoring systems. ShuffleFAC integrates Frequency-Aware convolution into an efficiency-oriented backbone using separable convolution, point-wise group convolution, and channel shuffle, enabling frequency-sensitive feature extraction with low computational cost. Experiments on the DeepShip dataset show that ShuffleFAC achieves competitive performance with substantially reduced complexity. In particular, ShuffleFAC ($γ=16$) attains a macro F1-score of 71.45 $\pm$ 1.18% using 39K parameters and 3.06M MACs, and achieves an inference latency of 6.05 $\pm$ 0.95ms on a Raspberry Pi. Compared with MicroNet0, it improves macro F1-score by 1.82 % while reducing model size by 9.7x and latency by 2.5x. These results indicate that ShuffleFAC is suitable for real-time embedded UATR.
format Preprint
id arxiv_https___arxiv_org_abs_2601_13679
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Ultra-Lightweight Network for Ship-Radiated Sound Classification on Embedded Deployment
Park, Sangwon
Kim, Dongjun
Byun, Sung-Hoon
Park, Sangwook
Sound
This letter presents ShuffleFAC, a lightweight acoustic model for ship-radiated sound classification in resource-constrained maritime monitoring systems. ShuffleFAC integrates Frequency-Aware convolution into an efficiency-oriented backbone using separable convolution, point-wise group convolution, and channel shuffle, enabling frequency-sensitive feature extraction with low computational cost. Experiments on the DeepShip dataset show that ShuffleFAC achieves competitive performance with substantially reduced complexity. In particular, ShuffleFAC ($γ=16$) attains a macro F1-score of 71.45 $\pm$ 1.18% using 39K parameters and 3.06M MACs, and achieves an inference latency of 6.05 $\pm$ 0.95ms on a Raspberry Pi. Compared with MicroNet0, it improves macro F1-score by 1.82 % while reducing model size by 9.7x and latency by 2.5x. These results indicate that ShuffleFAC is suitable for real-time embedded UATR.
title Ultra-Lightweight Network for Ship-Radiated Sound Classification on Embedded Deployment
topic Sound
url https://arxiv.org/abs/2601.13679