Quantitative Analysis of Primary Attribution Explainable Artificial Intelligence Methods for Remote Sensing Image Classification
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.
Code (1)
Tasks
ClassificationDecision MakingExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)image-classificationImage ClassificationRemote Sensing Image ClassificationSimilar Papers 제목 키워드 기반
Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy
Deep Neural Networks (DNNs) are known to be strong predictors, but their prediction strategies can rarely be understood. With recent advances in Explainable Artificial Intelligence (XAI), approaches are available to expl…
Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)On the Connection between Game-Theoretic Feature Attributions and Counterfactual Explanations
Explainable Artificial Intelligence (XAI) has received widespread interest in recent years, and two of the most popular types of explanations are feature attributions, and counterfactual explanations. These classes of ap…
counterfactualCounterfactual ExplanationExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)+1qZACH-ViT: Quantization-Aware Intrinsic Explanations with Recursive Attribution-Stabilized Optimization
Compact medical-image classifiers need efficiency and interpretable evidence, yet these goals are often addressed separately. We introduce qZACH-ViT, a quantization-aware extension of the zero-token (CLS-token-free), pos…
TEFL: Turbo Explainable Federated Learning for 6G Trustworthy Zero-Touch Network Slicing
Sixth-generation (6G) networks anticipate intelligently supporting a massive number of coexisting and heterogeneous slices associated with various vertical use cases. Such a context urges the adoption of artificial intel…
Explainable Artificial Intelligence (XAI)Federated LearningManagementDiffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution
Path-based attribution methods such as Integrated Gradients (IG) are widely adopted for their strong axiomatic properties and effectiveness in attributing model predictions to input features by integrating gradients alon…