Entropy-Centric Explainable AI for Remote Sensing Image Segmentation

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Ali Saleh, Abdul Karim Gizzini, Mohamad Ghassany, Ali J. Ghandour
• Venue: arXiv: cs.CV
• Published: 2026-08-11
• Collected: 2026-08-12
• URL: http://arxiv.org/abs/2608.11064v1
• PDF: https://arxiv.org/pdf/2608.11064v1
• DOI: UNKNOWN
• Registry group: academic_apis_and_preprints
• Evidence role: canonical_academic_index
• Language: en
• Country / region: UNKNOWN

Plain-Language Brief

This research paper introduces an explainable AI (XAI) method for image segmentation in remote sensing. The method is centered around entropy and aims to provide insights into the decision-making process of AI models. A new XAI evaluation methodology is also proposed, and experimental results suggest that this method outperforms other recently adapted XAI methods for semantic segmentation.

What the Document Says

• Artificial intelligence (AI) is used in critical domains to solve complex problems.
• Deep neural networks excel at tasks but lack transparency, causing concern in critical domains like remote sensing.
• Explainable AI (XAI) aims to clarify the decision-making process of AI models, which is essential in critical domains.
• The paper proposes an entropy-centric XAI method for semantic segmentation in remote sensing image analysis.
• A new XAI evaluation methodology is proposed to measure the relevance of regions highlighted by the XAI method.
• Experimental results indicate that the proposed XAI method outperforms other recent methods for semantic segmentation.

Key Concepts Mentioned

• Artificial Intelligence
• Deep Neural Networks
• Explainable AI (XAI)
• Entropy
• Semantic Segmentation
• Remote Sensing

Claims Made by the Document

• The lack of transparency in deep neural networks limits trust and adoption in critical domains like remote sensing.
• Explainable AI (XAI) can bridge the gap by providing insights into the decision-making process of AI models.
• The proposed entropy-centric XAI method is superior for semantic segmentation compared to other recent methods.

Evidence Used

• Not stated in source

Methods / Approach

• Entropy-centric Explainable AI method for semantic segmentation.
• A new XAI evaluation methodology.

Limitations Stated by the Authors

• No evidence provided to support claims made in the paper.

Limitations Noted by the Agent

Agent interpretation — not from the source.

• The study's generalizability is limited due to the absence of external validation.

Open Questions

• What specific remote sensing tasks were used for testing and evaluation?

Notes for Future Q&A

May include interpretation. Labeled where it does.

• It would be beneficial to explore the details of the experimental setup, such as the dataset used and the metrics employed for comparison.

Raw Abstract / Excerpt

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.