Quantitative Analysis of Primary Attribution Explainable Artificial Intelligence Methods for Remote Sensing Image Classification

TL;DR

This paper provides a comprehensive quantitative evaluation of XAI methods applied to remote sensing image classification, comparing their effectiveness across multiple modalities to guide better interpretability of machine learning models.

Contribution

It introduces a systematic framework for quantitatively assessing XAI techniques in remote sensing, offering insights and recommendations for selecting suitable explainability methods.

Findings

Identified the most effective XAI methods for remote sensing tasks

Provided a quantitative comparison across different XAI techniques

Offered practical guidelines for XAI method selection

Abstract

We present a comprehensive analysis of quantitatively evaluating explainable artificial intelligence (XAI) techniques for remote sensing image classification. Our approach leverages state-of-the-art machine learning approaches to perform remote sensing image classification across multiple modalities. We investigate the results of the models qualitatively through XAI methods. Additionally, we compare the XAI methods quantitatively through various categories of desired properties. Through our analysis, we offer insights and recommendations for selecting the most appropriate XAI method(s) to gain a deeper understanding of the models' decision-making processes. The code for this work is publicly available.