Explainable Systematic Analysis for Synthetic Aperture Sonar Imagery

TL;DR

This paper systematically analyzes how fine-tuning deep learning models on synthetic aperture sonar data affects performance, using explainability tools to identify key features and the importance of balanced datasets.

Contribution

It introduces an explainability framework for SAS imagery analysis and highlights the significance of data balance in model fine-tuning.

Findings

Improved seafloor texture classification accuracy.

Identified critical features influencing model performance.

Emphasized the importance of balanced training data.

Abstract

In this work, we present an in-depth and systematic analysis using tools such as local interpretable model-agnostic explanations (LIME) (arXiv:1602.04938) and divergence measures to analyze what changes lead to improvement in performance in fine tuned models for synthetic aperture sonar (SAS) data. We examine the sensitivity to factors in the fine tuning process such as class imbalance. Our findings show not only an improvement in seafloor texture classification, but also provide greater insight into what features play critical roles in improving performance as well as a knowledge of the importance of balanced data for fine tuning deep learning models for seafloor classification in SAS imagery.