Generalization to out-of-distribution (OOD) data is a capability natural to humans yet challenging for machines to reproduce. This is because most learning algorithms strongly rely on the i.i.d.~assumption on source/target data, which is often violated in practice due to domain shift. Domain generalization (DG) aims to achieve OOD generalization by using only source data for model learning. Since first introduced in 2011, research in DG has made great progresses. In particular, intensive research in this topic has led to a broad spectrum of methodologies, e.g., those based on domain alignment, meta-learning, data augmentation, or ensemble learning, just to name a few; and has covered various vision applications such as object recognition, segmentation, action recognition, and person re-identification. In this paper, for the first time a comprehensive literature review is provided to summarize the developments in DG for computer vision over the past decade. Specifically, we first cover the background by formally defining DG and relating it to other research fields like domain adaptation and transfer learning. Second, we conduct a thorough review into existing methods and present a categorization based on their methodologies and motivations. Finally, we conclude this survey with insights and discussions on future research directions.

翻译：向分配外(OOD)数据概括化是人类的一种自然能力,但对于机器复制来说却具有挑战性。这是因为大多数学习算法都强烈依赖源/目标数据的i.d.-sumputation,而由于领域转移,这种数据在实践中经常被违反。DG(DG)的目的是通过只使用源数据实现OOOD的概括化。自2011年首次引入以来,DG的研究取得了巨大进展。特别是,这个专题的密集研究导致了一系列广泛的方法,例如基于域对齐、元学习、数据增强或共同学习的方法,仅举几个例子;并涵盖各种视觉应用,如对象识别、分解、行动识别和个人再识别。本文首次提供了全面的文献审查,以总结过去十年中DG计算机愿景的发展动态。具体地说,我们首先通过正式界定DG,将其与其他研究领域如领域适应和转移学习领域联系起来,从而覆盖了背景。第二,我们对现有方法进行了彻底审查,并最后根据研究方向和动机,提出了关于未来研究方向的见解。