期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 45, 期 4, 页码 4396-4415出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2022.3195549
关键词
Data models; Speech recognition; Adaptation models; Face recognition; Soft sensors; Handwriting recognition; Biomedical imaging; Out-of-distribution generalization; domain shift; model robustness; machine learning
Domain generalization aims to achieve generalization to out-of-distribution data by using only source data for model learning. This paper provides a comprehensive literature review on the developments in domain generalization over the past decade, including the background, existing methods and theories, and insights and discussions on future research directions.
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. Over the last ten years, research in DG has made great progress, leading to a broad spectrum of methodologies, e.g., those based on domain alignment, meta-learning, data augmentation, or ensemble learning, to name a few; DG has also been studied in various application areas including computer vision, speech recognition, natural language processing, medical imaging, and reinforcement learning. In this paper, for the first time a comprehensive literature review in DG is provided to summarize the developments over the past decade. Specifically, we first cover the background by formally defining DG and relating it to other relevant fields like domain adaptation and transfer learning. Then, we conduct a thorough review into existing methods and theories. Finally, we conclude this survey with insights and discussions on future research directions.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据