Extending scene-to-patch models: Multi-resolution multiple instance learning for Earth observation
Extending scene-to-patch models: Multi-resolution multiple instance learning for Earth observation
Land cover classification (LCC) and natural disaster response (NDR) are important issues in climate change mitigation and adaptation. Existing approaches that use machine learning with Earth observation (EO) imaging data for LCC and NDR often rely on fully annotated and segmented datasets. Creating these datasets requires a large amount of effort, and a lack of suitable datasets has become an obstacle in scaling the use of machine learning for EO. In this study, we extend our prior work on Scene-to-Patch models: an alternative machine learning approach for EO that utilizes Multiple Instance Learning (MIL). As our approach only requires high-level scene labels, it enables much faster development of new datasets while still providing segmentation through patch-level predictions, ultimately increasing the accessibility of using machine learning for EO. We propose new multi-resolution MIL architectures that outperform single-resolution MIL models and non-MIL baselines on the DeepGlobe LCC and FloodNet NDR datasets. In addition, we conduct a thorough analysis of model performance and interpretability.
18
Early, Joseph
fd4e9e4c-9251-474d-a9cf-12157a9f2f73
Deweese, Ying-Jung Chen
827873a3-540f-4d03-8698-1d5f23b22131
Evers, Christine
93090c84-e984-4cc3-9363-fbf3f3639c4b
Ramchurn, Sarvapali
1d62ae2a-a498-444e-912d-a6082d3aaea3
Early, Joseph
fd4e9e4c-9251-474d-a9cf-12157a9f2f73
Deweese, Ying-Jung Chen
827873a3-540f-4d03-8698-1d5f23b22131
Evers, Christine
93090c84-e984-4cc3-9363-fbf3f3639c4b
Ramchurn, Sarvapali
1d62ae2a-a498-444e-912d-a6082d3aaea3
Early, Joseph, Deweese, Ying-Jung Chen, Evers, Christine and Ramchurn, Sarvapali
(2023)
Extending scene-to-patch models: Multi-resolution multiple instance learning for Earth observation.
Environmental Data Science, 2, , [e42].
(doi:10.1017/eds.2023.30).
Abstract
Land cover classification (LCC) and natural disaster response (NDR) are important issues in climate change mitigation and adaptation. Existing approaches that use machine learning with Earth observation (EO) imaging data for LCC and NDR often rely on fully annotated and segmented datasets. Creating these datasets requires a large amount of effort, and a lack of suitable datasets has become an obstacle in scaling the use of machine learning for EO. In this study, we extend our prior work on Scene-to-Patch models: an alternative machine learning approach for EO that utilizes Multiple Instance Learning (MIL). As our approach only requires high-level scene labels, it enables much faster development of new datasets while still providing segmentation through patch-level predictions, ultimately increasing the accessibility of using machine learning for EO. We propose new multi-resolution MIL architectures that outperform single-resolution MIL models and non-MIL baselines on the DeepGlobe LCC and FloodNet NDR datasets. In addition, we conduct a thorough analysis of model performance and interpretability.
Text
extending-scene-to-patch-models-multi-resolution-multiple-instance-learning-for-earth-observation
- Version of Record
More information
Accepted/In Press date: 1 September 2023
e-pub ahead of print date: 4 December 2023
Identifiers
Local EPrints ID: 490766
URI: http://eprints.soton.ac.uk/id/eprint/490766
PURE UUID: 2ab1ecad-458c-4088-8c72-c3383537d56d
Catalogue record
Date deposited: 06 Jun 2024 16:38
Last modified: 08 Jun 2024 02:00
Export record
Altmetrics
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
