Given multiple source domains, domain generalization aims at learning a universal model that performs well on any unseen but related target domain. In this work, we focus on the domain generalization scenario where domain shifts occur among class-conditional distributions of different domains. Existing approaches are not sufficiently robust when the variation of conditional distributions given the same class is large. In this work, we extend the concept of distributional robust optimization to solve the class-conditional domain generalization problem. Our approach optimizes the worst-case performance of a classifier over class-conditional distributions within a Wasserstein ball centered around the barycenter of the source conditional distributions. We also propose an iterative algorithm for learning the optimal radius of the Wasserstein balls automatically. Experiments show that the proposed framework has better performance on unseen target domain than approaches without domain generalization.

翻译：在多个源域下, 域一般化的目的是学习一种通用模式, 该模式在任何不可见但相关的目标域上运行良好。 在这项工作中, 我们侧重于不同域的等级条件分布发生域变换的域域一般化假设。 当同一类的有条件分布差异很大时, 现有办法不够健全。 在这项工作中, 我们扩展分配强力优化概念, 以解决等级域一般化问题 。 我们的方法优化了以源有条件分布的百分点为中心的一个瓦塞斯坦球中心为中心, 分类者在等级条件分布上的最坏的性能。 我们还提议了一个迭代算法, 用于自动学习瓦塞斯坦球的最佳半径。 实验显示, 拟议的框架在不可见的目标域域上比不使用全域化的方法有更好的性能 。