# Segmenting across places: The need for fair transfer learning with satellite imagery

arXiv: https://arxiv.org/abs/2204.04358 · HTML: https://mlsanity.com/paper/2204.04358/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 61 references that are in the map.
- First posted on arXiv 9 Apr 2022.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images](https://mlsanity.com/paper/1805.06561/) (2018)
- [LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2110.08733/) (2021)
- [Instance Adaptive Self-Training for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2008.12197/) (2020)
- [To be Robust or to be Fair: Towards Fairness in Adversarial Training](https://mlsanity.com/paper/2010.06121/) (2020)
- [A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery](https://mlsanity.com/paper/2010.08168/) (2020)
- [Robust Fairness under Covariate Shift](https://mlsanity.com/paper/2010.05166/) (2020)
- [Sample Selection for Fair and Robust Training](https://mlsanity.com/paper/2110.14222/) (2021)
- [Gated CRF Loss for Weakly Supervised Semantic Image Segmentation](https://mlsanity.com/paper/1906.04651/) (2019)
- [Transfer of Machine Learning Fairness across Domains](https://mlsanity.com/paper/1906.09688/) (2019)
- [Ensuring Fairness Beyond the Training Data](https://mlsanity.com/paper/2007.06029/) (2020)
- [RadFusion: Benchmarking Performance and Fairness for Multimodal Pulmonary Embolism Detection from CT and EHR](https://mlsanity.com/paper/2111.11665/) (2021)
- [Semi-Supervised Semantic Segmentation in Earth Observation: The MiniFrance Suite, Dataset Analysis and Multi-task Network Study](https://mlsanity.com/paper/2010.07830/) (2020)
- [Weakly Supervised Semantic Segmentation of Satellite Images for Land Cover Mapping -- Challenges and Opportunities](https://mlsanity.com/paper/2002.08254/) (2020)
- [Road Segmentation in SAR Satellite Images with Deep Fully-Convolutional Neural Networks](https://mlsanity.com/paper/1802.01445/) (2018)
- [Tilted Cross Entropy (TCE): Promoting Fairness in Semantic Segmentation](https://mlsanity.com/paper/2103.14051/) (2021)
- [The Need for Ethical, Responsible, and Trustworthy Artificial Intelligence for Environmental Sciences](https://mlsanity.com/paper/2112.08453/) (2021)
- [Satellite Imagery Feature Detection using Deep Convolutional Neural Network: A Kaggle Competition](https://mlsanity.com/paper/1706.06169/) (2017)
- [Weakly Supervised Domain Adaptation for Built-up Region Segmentation in Aerial and Satellite Imagery](https://mlsanity.com/paper/2007.02277/) (2020)
- [Local Context Normalization: Revisiting Local Normalization](https://mlsanity.com/paper/1912.05845/) (2019)
- [Deep Landscape Features for Improving Vector-borne Disease Prediction](https://mlsanity.com/paper/1904.01994/) (2019)
- [CNN-Based Semantic Change Detection in Satellite Imagery](https://mlsanity.com/paper/2006.05589/) (2020)
- [PP-LinkNet: Improving Semantic Segmentation of High Resolution Satellite Imagery with Multi-stage Training](https://mlsanity.com/paper/2010.06932/) (2020)

## Built on by (most cited first, 6 of 6)

- [EvoluNet: Advancing Dynamic Non-IID Transfer Learning on Graphs](https://mlsanity.com/paper/2305.00664/) (2023)
- [Fairness and representation in satellite-based poverty maps: Evidence of urban-rural disparities and their impacts on downstream policy](https://mlsanity.com/paper/2305.01783/) (2023)
- [S4: Self-Supervised Sensing Across the Spectrum](https://mlsanity.com/paper/2405.01656/) (2024)
- [Reflections from the Workshop on AI-Assisted Decision Making for Conservation](https://mlsanity.com/paper/2307.08774/) (2023)
- [Mitigating Urban-Rural Disparities in Contrastive Representation Learning with Satellite Imagery](https://mlsanity.com/paper/2211.08672/) (2022)
- [A Parameter-efficient Convolutional Approach for Camouflaged Weed Detection in Multispectral Aerial Imagery](https://mlsanity.com/paper/2603.06655/) (2026)

## Abstract (arXiv)

The increasing availability of high-resolution satellite imagery has enabled the use of machine learning to support land-cover measurement and inform policy-making. However, labelling satellite images is expensive and is available for only some locations. This prompts the use of transfer learning to adapt models from data-rich locations to others. Given the potential for high-impact applications of satellite imagery across geographies, a systematic assessment of transfer learning implications is warranted. In this work, we consider the task of land-cover segmentation and study the fairness implications of transferring models across locations. We leverage a large satellite image segmentation benchmark with 5987 images from 18 districts (9 urban and 9 rural). Via fairness metrics we quantify disparities in model performance along two axes -- across urban-rural locations and across land-cover classes. Findings show that state-of-the-art models have better overall accuracy in rural areas compared to urban areas, through unsupervised domain adaptation methods transfer learning better to urban versus rural areas and enlarge fairness gaps. In analysis of reasons for these findings, we show that raw satellite images are overall more dissimilar between source and target districts for rural than for urban locations. This work highlights the need to conduct fairness analysis for satellite imagery segmentation models and motivates the development of methods for fair transfer learning in order not to introduce disparities between places, particularly urban and rural locations.