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

TL;DR

This paper introduces an adversarial multi-task learning framework for underwater acoustic target recognition that enhances robustness against environmental and data collection variations, achieving state-of-the-art results.

Contribution

It proposes a novel multi-task adversarial approach to explicitly model and mitigate influential environmental factors in underwater acoustic recognition.

Findings

Achieves state-of-the-art accuracy on ShipsEar dataset

Effectively models environmental factors like water depth and wind speed

Enhances robustness of recognition system against environmental variability

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.