Leveraging Activation Maximization and Generative Adversarial Training to Recognize and Explain Patterns in Natural Areas in Satellite Imagery
Open Access
- 21 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21 (1545598X) , 1-5
Abstract
Natural protected areas are vital for biodiversity, climate change mitigation, and supporting ecological processes. Despite their significance, comprehensive mapping is hindered by a lack of understanding of their characteristics and a missing land cover class definition. This paper aims to advance the explanation of the designating patterns forming protected and wild areas. To this end, we propose a novel framework that uses activation maximization and a generative adversarial model. With this, we aim to generate satellite images that, in combination with domain knowledge, are capable of offering complete and valid explanations for the spatial and spectral patterns that define the natural authenticity of these regions. Our proposed framework produces more precise attribution maps pinpointing the designating patterns forming the natural authenticity of protected areas. Our approach fosters our understanding of the ecological integrity of the protected natural areas and may contribute to future monitoring and preservation efforts.Keywords
All Related Versions
Funding Information
- Deutsche Forschungsgemeinschaft [German Research Foundation (DFG)] under Germany’s Excellence Strategy (EXC-2070-390732324-PhenoRob)
This publication has 12 references indexed in Scilit:
- Explaining clinical decision support systems in medical imaging using cycle-consistent activation maximizationNeurocomputing, 2021
- Generative adversarial network: An overview of theory and applicationsInternational Journal of Information Management Data Insights, 2021
- Explainable AI: A Review of Machine Learning Interpretability MethodsEntropy, 2020
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based LocalizationInternational Journal of Computer Vision, 2019
- CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features2019
- Super-convergence: very fast training of neural networks using large learning rates2019
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
- Visualizing Deep Convolutional Neural Networks Using Natural Pre-imagesInternational Journal of Computer Vision, 2016
- Visualizing and Understanding Convolutional Networks2014
- Wilderness preservation and biodiversity conservation—keeping divergent goals distinctBioScience, 1999