Entropy-Centric Explainable AI for Remote Sensing Image Segmentation

2026-08-11

AI Summary

This study addresses the lack of transparency in deep model decisions for semantic segmentation of remote sensing imagery, which hinders their trustworthy deployment in critical applications. To this end, the work proposes the first explainable artificial intelligence (XAI) method tailored to remote sensing segmentation, centered on information entropy, and introduces a dedicated region-wise relevance evaluation paradigm to quantitatively assess the alignment between explanation outcomes and predicted semantics. Experimental results demonstrate that the proposed approach significantly outperforms existing XAI techniques adapted for segmentation tasks in terms of explanation fidelity, offering a novel pathway toward interpretable and reliable intelligent interpretation of remote sensing data.

Abstract

Artificial intelligence (AI) has become a powerful approach to solving complex problems in critical domains. Many concerns arise regarding the decision-making process of its models, mainly due to deep neural networks outperforming their peers at the cost of ambiguity in feature extraction and prediction. Consequently, in critical domains such as remote sensing, where high-resolution imagery must be analyzed using black-box models, the lack of transparency limits trust in these models and, thus, their adoption. In light of this reality, explaining and understanding the complex decision-making process of AI models has become essential. Explainable AI (XAI) aims to bridge this gap by providing insights into how and why certain decisions are made. While significant progress has been achieved in explaining image classification tasks, image segmentation still offers considerable room for improvement. In this context, this paper proposes an entropy-centric XAI method for semantic segmentation. Moreover, a new XAI evaluation methodology is proposed to efficiently measure the relevance of the regions highlighted by the proposed XAI method. Experimental results demonstrate the superiority of the proposed XAI method compared with recently adapted XAI methods for semantic segmentation.

Problem

• Explainable AI
• Semantic Segmentation
• Remote Sensing
• Model Transparency
• XAI Evaluation

Innovation

• Entropy-centric
• Explainable AI
• Semantic Segmentation
• Remote Sensing
• XAI Evaluation