# Learning to Interpret Satellite Images Using Wikipedia

arXiv: https://arxiv.org/abs/1809.10236 · HTML: https://mlsanity.com/paper/1809.10236/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2018.

## Built on by (most cited first, 12 of 12)

- [SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery](https://mlsanity.com/paper/2207.08051/) (2022)
- [Domino: Discovering Systematic Errors with Cross-Modal Embeddings](https://mlsanity.com/paper/2203.14960/) (2022)
- [GEO-Bench: Toward Foundation Models for Earth Monitoring](https://mlsanity.com/paper/2306.03831/) (2023)
- [Toward Foundation Models for Earth Monitoring: Proposal for a Climate Change Benchmark](https://mlsanity.com/paper/2112.00570/) (2021)
- [Contrastive Multiview Coding with Electro-optics for SAR Semantic Segmentation](https://mlsanity.com/paper/2109.00120/) (2021)
- [IS-COUNT: Large-scale Object Counting from Satellite Images with Covariate-based Importance Sampling](https://mlsanity.com/paper/2112.09126/) (2021)
- [WildSAT: Learning Satellite Image Representations from Wildlife Observations](https://mlsanity.com/paper/2412.14428/) (2024)
- [Land Cover Mapping in Limited Labels Scenario: A Survey](https://mlsanity.com/paper/2103.02429/) (2021)
- [EcoWikiRS: Learning Ecological Representation of Satellite Images from Weak Supervision with Species Observations and Wikipedia](https://mlsanity.com/paper/2504.19742/) (2025)
- [Terrain-Informed Self-Supervised Learning: Enhancing Building Footprint Extraction from LiDAR Data with Limited Annotations](https://mlsanity.com/paper/2311.01188/) (2023)
- [Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities](https://mlsanity.com/paper/2505.15870/) (2025)
- [A Weak Supervision Learning Approach Towards an Equitable Mobility Estimation](https://mlsanity.com/paper/2505.04229/) (2025)

## Abstract (arXiv)

Despite recent progress in computer vision, fine-grained interpretation of satellite images remains challenging because of a lack of labeled training data. To overcome this limitation, we propose using Wikipedia as a previously untapped source of rich, georeferenced textual information with global coverage. We construct a novel large-scale, multi-modal dataset by pairing geo-referenced Wikipedia articles with satellite imagery of their corresponding locations. To prove the efficacy of this dataset, we focus on the African continent and train a deep network to classify images based on labels extracted from articles. We then fine-tune the model on a human annotated dataset and demonstrate that this weak form of supervision can drastically reduce the quantity of human annotated labels and time required for downstream tasks.