Weiterentwicklung des Visuell-Sprachlichen Verständnisses in der Fernerkundung durch Deep Learning
Abstract
This dissertation explores deep learning-based vision-language understanding for remote sensing data. It focuses on developing effective strategies for visual question answering, extending to change detection-based visual question answering for temporal analysis, enhancing image understanding with pixel-level visual explanations, and leveraging large language models to create a high-quality image-text dataset.
Fields of Study & Subjects
Multimodal Machine Learning Applications
Remote-Sensing Image Classification
Advanced Neural Network Applications
Publication details
- Journal / source
- mediaTUM – the media and publications repository of the Technical University Munich (Technical University Munich)
- Publication date
- 9 January 2026
- Language
- EN
- Document type
- Thesis