Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Analysing Satellite Imagery Classification under Spatial Domain Shift across Geographic Regions

Domain:

geospatial

Record type:

datasetpaper
Creator:
SarYinFer
Host:avatar

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 github.com.

Other Information

Published in: International Journal of Computer Vision
License: https://creativecommons.org…
See article on publisher's website: https://dx.doi.org/10.1007/…

Visit

figshare.com

Tasks

image classificationcomputer vision

Tags

Information and computing sciencesArtificial intelligenceComputer vision and multimedia computationMachine learningDomain GeneralisationDistribution shiftOut-of-Distribution GeneralisationDomain ShiftLand Use ClassificationRemote Sensing

Licenses

CC BY 4.0

Similar

Intra-African Domain Shift in Wildlife Camera Trap AI]% {Intra-African Geographic Domain Shift in Wildlife Camera Trap Species Classification: A Comparative Study of Supervised and Zero-Shot Foundation ModelsConformal PM2.5 Mapping Under Spatial Covariate Shift: Satellite-Reanalysis Fusion for Africa's Green Industrial TransitionIntra-African Geographic Domain Shift in Wildlife Camera Trap Species Classification: A Comparative Study of Supervised and Zero-Shot Foundation ModelsCross-lingual NER Model Accuracy Degradation under Extreme Domain ShiftCrop classification dataset for testing domain adaptation or distributional shift methodsDeepAQ: Unsupervised Domain Adaptation for Air-Quality Mapping Using High-Resolution Satellite Imagery

Intra-African Domain Shift in Wildlife Camera Trap AI]% {Intra-African Geographic Domain Shift in Wildlife Camera Trap Species Classification: A Comparative Study of Supervised and Zero-Shot Foundation Models

This repository contains al

Conformal PM2.5 Mapping Under Spatial Covariate Shift: Satellite-Reanalysis Fusion for Africa's Green Industrial Transition

Africa's green industrialization imperative demands reliable infrastructure for monitoring air quali

Intra-African Geographic Domain Shift in Wildlife Camera Trap Species Classification: A Comparative Study of Supervised and Zero-Shot Foundation Models

Abstract Camera trap networks such as Snapshot Safari have generated millions of l

Cross-lingual NER Model Accuracy Degradation under Extreme Domain Shift

Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to ident

Crop classification dataset for testing domain adaptation or distributional shift methods

In this upload we share processed crop type datasets from both France and Kenya. These datasets can

DeepAQ: Unsupervised Domain Adaptation for Air-Quality Mapping Using High-Resolution Satellite Imagery

High-resolution urban air quality (AQ) estimation is critical for addressing problems such as quanti