arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.02503cs.LGcs.AIcs.CV
收藏

领域泛化研究综述

Domain Generalization: A Survey

Nanyang Technological University(南洋理工大学);Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Shanghai AI Lab(上海人工智能实验室);University of Surrey(萨里大学)

Kaiyang Zhou, Ziwei Liu, Yu Qiao, Tao Xiang, Chen Change Loy

摘要:

泛化到分发外(OOD)数据是人类的一种自然能力,但对机器来说是一种挑战。这是因为大多数学习算法强烈依赖于i.i.d.~假设的源/目标数据,这是经常违反在实践中,由于域转移。领域泛化(DG)的目标是通过只使用源数据进行模型学习来实现OOD泛化。在过去的十年里,DG的研究取得了很大的进展,导致了广泛的方法,例如,基于域对齐、元学习、数据增强或集成学习的那些,仅举几例; DG还在各种应用领域中被研究,包括计算机视觉、语音识别、自然语言处理、医学成像和强化学习。在本文中,第一次提供了一个全面的文献综述,在DG总结过去十年的发展。具体来说,我们首先覆盖的背景,正式定义DG和相关的其他相关领域,如领域自适应和迁移学习。然后,我们对现有的方法和理论进行了全面的回顾。最后,我们总结了这次调查的见解和讨论未来的研究方向。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑