Red Teaming Models for Hyperspectral Image Analysis Using Explainable AI
Warsaw University of Technology（华沙理工大学）；University of Warsaw（华沙大学）；Silesian University of Technology（西里西亚工业大学）；KP Labs（KP实验室）；European Space Agency（欧洲空间局）
Vladimir Zaigrajew, Hubert Baniecki, Lukasz Tulczyjew, Agata M. Wijata, Jakub Nalepa, Nicolas Longépé, Przemyslaw Biecek
Remote sensing (RS) applications in the space domain demand machine learning (ML) models that are reliable, robust, and quality-assured, making red teaming a vital approach for identifying and exposing potential flaws and biases. Since both fields advance independently, there is a notable gap in integrating red teaming strategies into RS. This paper introduces a methodology for examining ML models operating on hyperspectral images within the HYPERVIEW challenge, focusing on soil parameters' estimation. We use post-hoc explanation methods from the Explainable AI (XAI) domain to critically assess the best performing model that won the HYPERVIEW challenge and served as an inspiration for the model deployed on board the INTUITION-1 hyperspectral mission. Our approach effectively red teams the model by pinpointing and validating key shortcomings, constructing a model that achieves comparable performance using just 1% of the input features and a mere up to 5% performance loss. Additionally, we propose a novel way of visualizing explanations that integrate domain-specific information about hyperspectral bands (wavelengths) and data transformations to better suit interpreting models for hyperspectral image analysis.
A Comprehensive Survey for Hyperspectral Image Classification: The Evolution from Conventional to Transformers and Mamba Models
Department of Computer Science, National University of Computer and Emerging Sciences（计算机科学系，国立计算机与新兴科学大学）；Dipartimento di Matematica e Informatica-MIFT, University of Messina（数学与信息学系-MIFT，墨西拿大学）；School of Computer Science, University of Hull（计算机科学学院，赫尔大学）；Institute of Software Development and Engineering, Innopolis University（软件开发与工程研究所，因诺波利斯大学）；Aerospace Information Research Institute, Chinese Academy of Sciences（航空信息研究所，中国科学院）；Big Geospatial Data Management, Technical University of Munich（大规模地理空间数据管理，慕尼黑技术大学）；Department of Infrastructure Engineering, University of Melbourne（基础设施工程系，墨尔本大学）；Intelligent Control Laboratory, PLA Rocket Force University of Engineering（智能控制实验室，中国人民解放军火箭军工程大学）；Institute of Methodologies for Environmental Analysis, National Research Council（环境分析方法研究所，国家研究理事会）；School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences（电子、电气与通信工程学院，中国科学院大学）
