Analysing Satellite Imagery Classification under Spatial Domain Shift across Geographic Regions
Open Access
- 8 August 2025
- journal article
- research article
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (11) , 7672-7709
Abstract
Deep learning models are designed based on the i.i.d. assumption; consequently, they experience a significant performance drop due to the distribution shifts when deployed in real environments. Domain Generalisation (DG) aims to bridge the distribution shift between the source and target domains by improving the generalisability of the model to Out-Of-Distribution (OOD) data. This challenge is prominent in satellite imagery classification due to the scarcity of data from underrepresented regions such as Africa and Oceania. In this paper, we address the limitations of existing datasets in capturing distribution shifts caused by geospatial differences between geographic regions by constructing a new, large-scale dataset called Domain Shift across Geographic Regions (DSGR). This dataset aims to help researchers better understand the impact of distribution shifts on satellite imagery classification. Furthermore, we perform rigorous experiments on DSGR to investigate and benchmark the robustness of existing DG techniques under single- and multi-source domain settings and the role of foundation models in enhancing the DG techniques. Our evaluations reveal that recent DG techniques have a comparable, yet weak, performance on DSGR. However, when combined with a foundation model like CLIP, ERM (introduced in 1999) achieves highly competitive results, surpassing even recent state-of-the-art DG solutions in enhancing the generalisability of deep learning models across different geographic regions. Our dataset and code are available at https://github.com/RWGAI/DSGR .Keywords
Funding Information
- Hamad Bin Khalifa University
This publication has 47 references indexed in Scilit:
- Multi-temporal forest monitoring in the Swiss Alps with knowledge-guided deep learningRemote Sensing of Environment, 2024
- Transfer learning in environmental remote sensingRemote Sensing of Environment, 2023
- A self-evolving deep learning algorithm for automatic oil spill detection in Sentinel-1 SAR imagesRemote Sensing of Environment, 2023
- Cross-spatiotemporal land-cover classification from VHR remote sensing images with deep learning based domain adaptationISPRS Journal of Photogrammetry and Remote Sensing, 2022
- Integrating remote sensing and social sensing for flood mappingRemote Sensing Applications: Society and Environment, 2022
- Satellite-based data fusion crop type classification and mapping in Rio Grande do Sul, BrazilISPRS Journal of Photogrammetry and Remote Sensing, 2021
- Multimodal deep learning from satellite and street-level imagery for measuring income, overcrowding, and environmental deprivation in urban areasRemote Sensing of Environment, 2021
- A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning2020
- Deep CORAL: Correlation Alignment for Deep Domain Adaptation2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015