Adversarial multi-task underwater acoustic target recognition: Toward robustness against various influential factors

Yuan Xie; Ji Xu; Jiawei Ren; Junfeng Li

doi:10.1121/10.0026598

Adversarial multi-task underwater acoustic target recognition: Toward robustness against various influential factors

J Acoust Soc Am. 2024 Jul 1;156(1):299-313. doi: 10.1121/10.0026598.

Authors

Yuan Xie^{1

2}, Ji Xu^{1

2

3}, Jiawei Ren^{1

2}, Junfeng Li^{1

2}

Affiliations

¹ Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China.
² University of Chinese Academy of Sciences, Beijing 100190, China.
³ State Key Laboratory of Acoustics, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China.

PMID: 38984811
DOI: 10.1121/10.0026598

Abstract

Underwater acoustic target recognition based on passive sonar faces numerous challenges in practical maritime applications. One of the main challenges lies in the susceptibility of signal characteristics to diverse environmental conditions and data acquisition configurations, which can lead to instability in recognition systems. While significant efforts have been dedicated to addressing these influential factors in other domains of underwater acoustics, they are often neglected in the field of underwater acoustic target recognition. To overcome this limitation, this study designs auxiliary tasks that model influential factors (e.g., source range, water column depth, or wind speed) based on available annotations and adopts a multi-task framework to connect these factors to the recognition task. Furthermore, we integrate an adversarial learning mechanism into the multi-task framework to prompt the model to extract representations that are robust against influential factors. Through extensive experiments and analyses on the ShipsEar dataset, our proposed adversarial multi-task model demonstrates its capacity to effectively model the influential factors and achieve state-of-the-art performance on the 12-class recognition task.