Deep Neural Network Explainability Enhancement via Causality-Erasing SHAP Method for SAR Target Recognition

Deep neural networks (DNN)s have shown remarkable effectiveness in synthetic aperture radar (SAR) target recognition. However, the explainability problem for DNNs remains insufficiently addressed. One approach to tackle this challenge is the SHAP method. It enhances the explainability of DNNs in SAR target recognition by observing how the target, shadow, and clutter regions play their own distinct roles. The masked regions are typically filled with zero, mean, or random values in optical images. But if the same operation is performed on SAR images, it will affect the distribution of clutter and thus introducing new out-of-distribution (OOD) challenge. In this article, we propose a novel masking method to enhance the reliability and efficiency of the SHAP method in SAR-ATR applications. Experimental results on the MSTAR and OpenSARShip-1.0 datasets demonstrate that our proposed method provides a more faithful representation to show the importance of every single regions in SAR target recognition. Compared to methods using zero values, mean values, and random baselines, our proposed method significantly enhances the reliability of explainability.