# Continental-Scale Building Detection from High Resolution Satellite Imagery

arXiv: https://arxiv.org/abs/2107.12283 · HTML: https://mlsanity.com/paper/2107.12283/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 20 references that are in the map.
- First posted on arXiv 26 Jul 2021.

## Builds on (most cited first, 15 of 15)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Hybrid Task Cascade for Instance Segmentation](https://mlsanity.com/paper/1901.07518/) (2019)
- [DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images](https://mlsanity.com/paper/1805.06561/) (2018)
- [Scaled-YOLOv4: Scaling Cross Stage Partial Network](https://mlsanity.com/paper/2011.08036/) (2020)
- [SpaceNet: A Remote Sensing Dataset and Challenge Series](https://mlsanity.com/paper/1807.01232/) (2018)
- [Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping](https://mlsanity.com/paper/1510.00098/) (2015)
- [TernausNetV2: Fully Convolutional Network for Instance Segmentation](https://mlsanity.com/paper/1806.00844/) (2018)

## Built on by (most cited first, 30 of 50)

- [OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mapping](https://mlsanity.com/paper/2210.10732/) (2022)
- [TorchGeo: Deep Learning With Geospatial Data](https://mlsanity.com/paper/2111.08872/) (2021)
- [Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidar](https://mlsanity.com/paper/2304.07213/) (2023)
- [Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data](https://mlsanity.com/paper/2401.17600/) (2024)
- [METER-ML: A Multi-Sensor Earth Observation Benchmark for Automated Methane Source Mapping](https://mlsanity.com/paper/2207.11166/) (2022)
- [High-Resolution Building and Road Detection from Sentinel-2](https://mlsanity.com/paper/2310.11622/) (2023)
- [IS-COUNT: Large-scale Object Counting from Satellite Images with Covariate-based Importance Sampling](https://mlsanity.com/paper/2112.09126/) (2021)
- [3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions](https://mlsanity.com/paper/2404.04823/) (2024)
- [MapFormer: Boosting Change Detection by Using Pre-change Information](https://mlsanity.com/paper/2303.17859/) (2023)
- [Fast building segmentation from satellite imagery and few local labels](https://mlsanity.com/paper/2206.05377/) (2022)
- [Fine-grained Population Mapping from Coarse Census Counts and Open Geodata](https://mlsanity.com/paper/2211.04039/) (2022)
- [High-resolution Population Maps Derived from Sentinel-1 and Sentinel-2](https://mlsanity.com/paper/2311.14006/) (2023)
- [Robust Disaster Assessment from Aerial Imagery Using Text-to-Image Synthetic Data](https://mlsanity.com/paper/2405.13779/) (2024)
- [Submeter-level Land Cover Mapping of Japan](https://mlsanity.com/paper/2311.11252/) (2023)
- [The State of Computer Vision Research in Africa](https://mlsanity.com/paper/2401.11617/) (2024)
- [TEMPO: Global Temporal Building Density and Height Estimation from Satellite Imagery](https://mlsanity.com/paper/2511.12104/) (2025)
- [Localized, High-resolution Geographic Representations with Slepian Functions](https://mlsanity.com/paper/2602.00392/) (2026)
- [Towards a Better Understanding of the Computer Vision Research Community in Africa](https://mlsanity.com/paper/2305.06773/) (2023)
- [Benchmarking Individual Tree Mapping with Sub-meter Imagery](https://mlsanity.com/paper/2311.07981/) (2023)
- [UB-FineNet: Urban Building Fine-grained Classification Network for Open-access Satellite Images](https://mlsanity.com/paper/2403.02132/) (2024)
- [GlobalBuildingMap -- Unveiling the Mystery of Global Buildings](https://mlsanity.com/paper/2404.13911/) (2024)
- [Cross Pseudo Supervision Framework for Sparsely Labelled Geospatial Images](https://mlsanity.com/paper/2408.02382/) (2024)
- [Large-scale School Mapping using Weakly Supervised Deep Learning for Universal School Connectivity](https://mlsanity.com/paper/2412.14870/) (2024)
- [DeepC4: Deep Conditional Census-Constrained Clustering for Large-scale Multitask Spatial Disaggregation of Urban Morphology](https://mlsanity.com/paper/2507.22554/) (2025)
- [Multi-AI Complex Systems in Humanitarian Response](https://mlsanity.com/paper/2208.11282/) (2022)
- [Building Coverage Estimation with Low-resolution Remote Sensing Imagery](https://mlsanity.com/paper/2301.01449/) (2023)
- [Estimating Residential Solar Potential Using Aerial Data](https://mlsanity.com/paper/2306.13564/) (2023)
- [Global Mapping of Exposure and Physical Vulnerability Dynamics in Least Developed Countries using Remote Sensing and Machine Learning](https://mlsanity.com/paper/2404.01748/) (2024)
- [CMAB: A First National-Scale Multi-Attribute Building Dataset in China Derived from Open Source Data and GeoAI](https://mlsanity.com/paper/2408.05891/) (2024)
- [Oya: Deep Learning for Accurate Global Precipitation Estimation](https://mlsanity.com/paper/2511.10562/) (2025)

## Abstract (arXiv)

Identifying the locations and footprints of buildings is vital for many practical and scientific purposes. Such information can be particularly useful in developing regions where alternative data sources may be scarce. In this work, we describe a model training pipeline for detecting buildings across the entire continent of Africa, using 50 cm satellite imagery. Starting with the U-Net model, widely used in satellite image analysis, we study variations in architecture, loss functions, regularization, pre-training, self-training and post-processing that increase instance segmentation performance. Experiments were carried out using a dataset of 100k satellite images across Africa containing 1.75M manually labelled building instances, and further datasets for pre-training and self-training. We report novel methods for improving performance of building detection with this type of model, including the use of mixup (mAP +0.12) and self-training with soft KL loss (mAP +0.06). The resulting pipeline obtains good results even on a wide variety of challenging rural and urban contexts, and was used to create the Open Buildings dataset of 516M Africa-wide detected footprints.