@inproceedings{65b69559399648a290e0d2024fd619a3,
title = "Mismatch-Robust Underwater Acoustic Localization Using A Differentiable Modular Forward Model",
abstract = "In this paper, we study the underwater acoustic localization in the presence of environmental mismatch. Especially, we exploit a pre-trained neural network for the acoustic wave propagation in a gradient-based optimization framework to estimate the source location. To alleviate the effect of mismatch between the training data and the test data, we simultaneously optimize over the network weights at the inference time, and provide conditions under which this method is effective. Moreover, we introduce a physics-inspired modularity in the forward model that enables us to learn the path lengths of the multipath structure in an end-to-end training manner without access to the specific path labels. We investigate the validity of the assumptions in a simple yet illustrative environment model.",
keywords = "few-shot adaptation, forward modeling, mismatch, physics-inspired modeling, test time adaptation, underwater acoustic",
author = "Dariush Kari and Yongjie Zhuang and Singer, {Andrew C.}",
note = "This work has been supported by the Office of Naval Research (ONR) under grant N00014-19-1-2662.; 59th Annual Conference on Information Sciences and Systems, CISS 2025 ; Conference date: 19-03-2025 Through 21-03-2025",
year = "2025",
doi = "10.1109/CISS64860.2025.10944684",
language = "English (US)",
series = "2025 59th Annual Conference on Information Sciences and Systems, CISS 2025",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2025 59th Annual Conference on Information Sciences and Systems, CISS 2025",
address = "United States",
}