Explainable Systematic Analysis for Synthetic Aperture Sonar Imagery
This work provides insights into improving seafloor classification for sonar imagery analysis, which is an incremental gain for researchers and practitioners in underwater acoustics and remote sensing.
This paper analyzes fine-tuned models for synthetic aperture sonar (SAS) data using LIME and divergence measures. The authors found an improvement in seafloor texture classification and gained insight into critical features and the importance of balanced data for fine-tuning deep learning models.
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.