Joint Source-Environment Adaptation for Deep Learning-Based Underwater Acoustic Source Ranging
This work addresses the challenge of deploying acoustic localization models in varying underwater environments, but it is incremental as it builds on existing domain adaptation techniques.
The paper tackles the problem of adapting a pre-trained deep learning model for underwater acoustic source ranging to a new environment without labeled data, using unsupervised domain adaptation and coupling it with signal energy estimation, resulting in improved generalization performance as demonstrated on simulated data with real ocean noise.
In this paper, we propose a method to adapt a pre-trained deep-learning-based model for underwater acoustic localization to a new environment. We use unsupervised domain adaptation to improve the generalization performance of the model, i.e., using an unsupervised loss, fine-tune the pre-trained network parameters without access to any labels of the target environment or any data used to pre-train the model. This method improves the pre-trained model prediction by coupling that with an almost independent estimation based on the received signal energy (that depends on the source). We show the effectiveness of this approach on Bellhop generated data in an environment similar to that of the SWellEx-96 experiment contaminated with real ocean noise from the KAM11 experiment.