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

Akshatha Mohan, Joshua Peeples
6/6/2023
cs.LGcs.AIcs.CV

No official code found. Best implementation: Advanced-Vision-and-Learning-Lab/XAI_Analysis (9 stars, MIT, last commit 2023-12-02).

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.

View on arXivView PDF

Code Implementations(1)

Advanced-Vision-and-Learning-Lab/XAI_AnalysisCommunity100%
MIT
91PythonMay 31, 20232 years agoMIT

Similar Papers

Example-Based Explainable AI and its Application for Remote Sensing Image Classification

88% match2023

Opening the Black-Box: A Systematic Review on Explainable AI in Remote Sensing

88% match2024

On the Effectiveness of Methods and Metrics for Explainable AI in Remote Sensing Image Scene Classification

87% match2025

Explainable AI for Earth Observation: Current Methods, Open Challenges, and Opportunities

86% match2023

RSMamba: Remote Sensing Image Classification with State Space Model

82% match1 repo3052024

Vision Foundation Models in Remote Sensing: A Survey

82% match1 repo522024

Cite this paper

@article{mohan2023quantitative,
  title  = {Quantitative Analysis of Primary Attribution Explainable Artificial Intelligence Methods for Remote Sensing Image Classification},
  author = {Akshatha Mohan and Joshua Peeples},
  year   = {2023},
  eprint = {2306.04037},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.04037v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.04037.svg)](https://codeofpaper.com/paper/2306.04037)

Discussion