Existing domain generalization aims to learn a generalizable model to perform well even on unseen domains. For many real-world machine learning applications, the data distribution often shifts gradually along domain indices. For example, a self-driving car with a vision system drives from dawn to dusk, with the sky darkening gradually. Therefore, the system must be able to adapt to changes in ambient illumination and continue to drive safely on the road. In this paper, we formulate such problems as Evolving Domain Generalization, where a model aims to generalize well on a target domain by discovering and leveraging the evolving pattern of the environment. We then propose Directional Domain Augmentation (DDA), which simulates the unseen target features by mapping source data as augmentations through a domain transformer. Specifically, we formulate DDA as a bi-level optimization problem and solve it through a novel meta-learning approach in the representation space. We evaluate the proposed method on both synthetic datasets and realworld datasets, and empirical results show that our approach can outperform other existing methods.

翻译：现有域泛化旨在学习一个可泛化的模型，使其在未见过的域上也能表现良好。在许多现实世界的机器学习应用中，数据分布常沿域索引逐渐偏移。例如，配备视觉系统的自动驾驶汽车从黎明行驶至黄昏，天空逐渐变暗。因此，系统必须能够适应环境光照的变化，并继续在道路上安全行驶。本文将此类问题形式化为演化域泛化，其中模型通过发现并利用环境的演化模式，旨在目标域上实现良好泛化。我们进而提出定向域增强（DDA），该方法通过域变换器将源数据映射为增强数据，从而模拟未见过的目标特征。具体而言，我们将DDA构建为双层优化问题，并通过一种新颖的元学习方法在表示空间中求解。我们在合成数据集和真实数据集上评估了所提方法，实验结果表明，我们的方法优于现有其他方法。