Explainable Analysis of Deep Learning Methods for SAR Image Classification
This work addresses the black-box problem for researchers and practitioners in remote sensing, but it is incremental as it applies existing XAI methods to a specific dataset.
The authors tackled the lack of interpretability in deep learning models for SAR image classification by applying explainable AI methods, finding that Occlusion achieved the most reliable interpretation with high Max-Sensitivity but low-resolution heatmaps.
Deep learning methods exhibit outstanding performance in synthetic aperture radar (SAR) image interpretation tasks. However, these are black box models that limit the comprehension of their predictions. Therefore, to meet this challenge, we have utilized explainable artificial intelligence (XAI) methods for the SAR image classification task. Specifically, we trained state-of-the-art convolutional neural networks for each polarization format on OpenSARUrban dataset and then investigate eight explanation methods to analyze the predictions of the CNN classifiers of SAR images. These XAI methods are also evaluated qualitatively and quantitatively which shows that Occlusion achieves the most reliable interpretation performance in terms of Max-Sensitivity but with a low-resolution explanation heatmap. The explanation results provide some insights into the internal mechanism of black-box decisions for SAR image classification.