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.

翻译：当训练数据集中地球位置分布与推理时观测到的分布存在差异时，便会产生地理分布偏移。在此场景下使用标准经验风险最小化（ERM）可能导致跨不同空间划分目标群组（如大洲或生物群落）的泛化性能不均衡。当前处理地理分布偏移的主流方法采用基于离散群组标签的域适应方法，忽略了通常作为元数据提供的地理坐标信息。另一方面，已有研究表明整合地理坐标的建模方法能提升整体性能，但其对地理域泛化的影响尚未得到系统研究。本工作提出一个提升地理分布偏移鲁棒性的通用建模框架，其核心思想是通过位置编码器建模连续的潜在域分配，并将主任务预测器与联合训练的潜在变量进行条件化。在四个具有不同群组划分的多样化地理标记图像数据集上，我们证明该框架的实例相比现有域适应方法和位置感知建模方法，在最差群组性能上实现了显著提升。特别地，我们在WILDS基准测试中的两个数据集上取得了新的最先进结果。