CVPR Findings2026
Latent Domain Modeling Improves Robustness to Geographic Shifts
Ruth Crasto, Esther Rolf
Abstract
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. Our code is publicly
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Improving Out-of-Distribution Robustness via Selective Augmentation cites WILDS: A Benchmark of in-the-Wild Distribution Shifts
- GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization cites Learning Transferable Visual Models From Natural Language Supervision
Builds on12
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- WILDS: A Benchmark of in-the-Wild Distribution ShiftsPang Wei Koh, Shiori Sagawa, Henrik Marklund, Sang Michael Xie et al.ICML 2021 · 1,773 citations
- Distributionally Robust Neural NetworksShiori Sagawa, Pang Wei Koh, Tatsunori B. Hashimoto, Percy LiangICLR 2020 · 1,578 citations
- GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localizationVicente Vivanco Cepeda, Gaurav Kumar Nayak, Mubarak ShahNeurIPS 2023 · 303 citations
- Improving Out-of-Distribution Robustness via Selective AugmentationHuaxiu Yao, Yu Wang, Sai Li, Linjun Zhang et al.ICML 2022 · 275 citations
Related papers
- GeoNet: Benchmarking Unsupervised Adaptation across GeographiesTarun Kalluri, Wangdong Xu, Manmohan ChandrakerCVPR 2023
- Benchmarking Object Detectors under Real-World Distribution Shifts in Satellite ImagerySara A. Al-Emadi, Yin Yang, Ferda OfliCVPR 2025
- Extending the WILDS Benchmark for Unsupervised AdaptationShiori Sagawa, Pang Wei Koh, Tony Lee, Irena Gao et al.ICLR 2022 · 116 citations
- GeoSURGE: Geo-localization using Semantic Fusion with Hierarchy of Geographic EmbeddingsAngel Daruna, Nicholas Meegan, Han-Pang Chiu, Supun Samarasekera et al.CVPR 2026 · 2 citations
- Adaptive Methods for Real-World Domain GeneralizationAbhimanyu Dubey, Vignesh Ramanathan, Alex Pentland, Dhruv MahajanCVPR 2021
