We address the task of domain generalization, where the goal is to train a predictive model based on a number of domains such that it is able to generalize to a new, previously unseen domain. We choose a generative approach within the framework of variational autoencoders and propose a weakly supervised algorithm that is able to account for incomplete and hierarchical domain information. We show that our method is able to learn representations that disentangle domain-specific information from class-label specific information even in complex settings where an unobserved substructure is present in domains. Our interpretable method outperforms previously proposed generative algorithms for domain generalization and achieves competitive performance compared to state-of-the-art approaches, which are based on complex image-processing steps, on the standard domain generalization benchmark dataset PACS.

翻译：我们处理的是域的概括化任务,其目标是在一系列领域的基础上培训一种预测模型,以便它能够概括到新的、先前看不见的领域。我们选择了一种在变异自动转换器框架内的基因化方法,并提出了一种监督不力的算法,能够说明不完全和等级的域信息。我们表明,我们的方法能够从分类标签特定信息中了解到将特定域信息与分类特定信息分离的表象,即使在一些领域存在未观测到的子结构的复杂环境中也是如此。我们的可解释方法优于先前提议的域化遗传化算法,并取得了与最先进的方法相比的竞争性性能,后者以复杂的图像处理步骤为基础,以标准的域通用基准数据集PACS为基础。