Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary Environment
This addresses the challenge of adapting machine learning models, such as in self-driving cars, to gradual environmental changes like lighting shifts, though it appears incremental as it builds on existing domain generalization work.
The paper tackles the problem of domain generalization in non-stationary environments, where data distributions shift gradually, and proposes Directional Domain Augmentation (DDA) to simulate unseen target features, achieving better performance than existing methods in empirical evaluations.
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.