Balsebre, P., Huang, W. orcid.org/0000-0002-3208-4208, Cong, G. et al. (1 more author) (2024) City Foundation Models for Learning General Purpose Representations from OpenStreetMap. In: CIKM '24: Proceedings of the 33rd ACM International Conference on Information and Knowledge Management. 33rd ACM International Conference on Information and Knowledge Management, 21-25 Oct 2024, Boise, USA. Association for Computing Machinery (ACM) , pp. 87-97. ISBN 9798400704369
Abstract
Pre-trained Foundation Models (PFMs) have ushered in a paradigm-shift in AI, due to their ability to learn general-purpose representations that can be readily employed in downstream tasks. While PFMs have been successfully adopted in various fields such as NLP and Computer Vision, their capacity in handling geospatial data remains limited. This can be attributed to the intrinsic heterogeneity of such data, which encompasses different types, including points, segments and regions, as well as multiple information modalities. The proliferation of Volunteered Geographic Information initiatives, like OpenStreetMap, unveils a promising opportunity to bridge this gap. In this paper, we present CityFM, a self-supervised framework to train a foundation model within a selected geographical area. CityFM relies solely on open data from OSM, and produces multimodal representations, incorporating spatial, visual, and textual information. We analyse the entity representations generated by our foundation models from a qualitative perspective, and conduct experiments on road, building, and region-level downstream tasks. In all the experiments, CityFM achieves performance superior to, or on par with, application-specific algorithms.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2024 Copyright held by the owner/author(s). This is an open access conference paper under the terms of the Creative Commons Attribution License (CC-BY 4.0), which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited. |
Keywords: | geospatial data, foundation models, contrastive learning |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Environment (Leeds) > School of Geography (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 13 Mar 2025 13:39 |
Last Modified: | 13 Mar 2025 13:39 |
Status: | Published |
Publisher: | Association for Computing Machinery (ACM) |
Identification Number: | 10.1145/3627673.3679662 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:224349 |