# Latent Domain Modeling Improves Robustness to Geographic Shifts

arXiv: https://arxiv.org/abs/2503.02036 · HTML: https://mlsanity.com/paper/2503.02036/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 3 Mar 2025.

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Functional Map of the World](https://mlsanity.com/paper/1711.07846/) (2017)
- [Improving Out-of-Distribution Robustness via Selective Augmentation](https://mlsanity.com/paper/2201.00299/) (2022)
- [GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization](https://mlsanity.com/paper/2309.16020/) (2023)
- [SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery](https://mlsanity.com/paper/2311.17179/) (2023)
- [Presence-Only Geographical Priors for Fine-Grained Image Classification](https://mlsanity.com/paper/1906.05272/) (2019)
- [Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells](https://mlsanity.com/paper/2003.00824/) (2020)
- [A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery](https://mlsanity.com/paper/2010.08168/) (2020)
- [CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations](https://mlsanity.com/paper/2305.01118/) (2023)
- [Sphere2Vec: A General-Purpose Location Representation Learning over a Spherical Surface for Large-Scale Geospatial Predictions](https://mlsanity.com/paper/2306.17624/) (2023)
- [Improving Image Classification with Location Context](https://mlsanity.com/paper/1505.03873/) (2015)
- [TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning](https://mlsanity.com/paper/2406.15658/) (2024)
- [Out-of-Domain Robustness via Targeted Augmentations](https://mlsanity.com/paper/2302.11861/) (2023)
- [Improving Domain Generalization with Domain Relations](https://mlsanity.com/paper/2302.02609/) (2023)
- [Active Learning-Based Species Range Estimation](https://mlsanity.com/paper/2311.02061/) (2023)
- [Distribution Shifts at Scale: Out-of-distribution Detection in Earth Observation](https://mlsanity.com/paper/2412.13394/) (2024)
- [Fast building segmentation from satellite imagery and few local labels](https://mlsanity.com/paper/2206.05377/) (2022)
- [Domain Conditional Predictors for Domain Adaptation](https://mlsanity.com/paper/2106.13899/) (2021)

## Built on by (most cited first, 1 of 1)

- [A Proxy Consistency Loss for Grounded Fusion of Earth Observation and Location Encoders](https://mlsanity.com/paper/2604.18881/) (2026)

## Abstract (arXiv)

Geographic distribution shift arises when the distribution of locations on Earth in a training dataset is different from what is seen at inference time. Using standard empirical risk minimization (ERM) in this setting can lead to uneven generalization across different spatially-determined groups of interest such as continents or biomes. The most common approaches to tackling geographic distribution shift apply domain adaptation methods using discrete group labels, ignoring geographic coordinates that are often available as metadata. On the other hand, modeling methods that integrate geographic coordinates have been shown to improve overall performance, but their impact on geographic domain generalization has not been studied. In this work, we propose a general modeling framework for improving robustness to geographic distribution shift. The key idea is to model continuous, latent domain assignment using location encoders and to condition the main task predictor on the jointly-trained latents. On four diverse geo-tagged image datasets with different group splits, we show that instances of our framework achieve significant improvements in worst-group performance compared to existing domain adaptation and location-aware modeling methods. In particular, we achieve new state-of-the-art results on two datasets from the WILDS benchmark.