Deep learning has been highly successful in computer vision with large amounts of labeled data, but struggles with limited labeled training data. To address this, Few-shot learning (FSL) is proposed, but it assumes that all samples (including source and target task data, where target tasks are performed with prior knowledge from source ones) are from the same domain, which is a stringent assumption in the real world. To alleviate this limitation, Cross-domain few-shot learning (CDFSL) has gained attention as it allows source and target data from different domains and label spaces. This paper provides a comprehensive review of CDFSL at the first time, which has received far less attention than FSL due to its unique setup and difficulties. We expect this paper to serve as both a position paper and a tutorial for those doing research in CDFSL. This review first introduces the definition of CDFSL and the issues involved, followed by the core scientific question and challenge. A comprehensive review of validated CDFSL approaches from the existing literature is then presented, along with their detailed descriptions based on a rigorous taxonomy. Furthermore, this paper outlines and discusses several promising directions of CDFSL that deserve further scientific investigation, covering aspects of problem setups, applications and theories.

翻译：深度学习在有大量标注数据的计算机视觉任务中取得了巨大成功，但在标注训练数据有限的情况下表现不佳。为解决该问题，研究者提出了小样本学习（FSL），但其假设所有样本（包括源任务和目标任务数据，其中目标任务利用源任务的先验知识）来自同一领域，这在现实世界中是一个严格的假设。为缓解这一限制，跨领域小样本学习（CDFSL）因允许源数据和目标数据来自不同领域和标签空间而受到关注。本文首次全面综述CDFSL——由于其独特的设定和难点，该领域受到的关注远少于FSL。我们期望本文能为从事CDFSL研究的人员提供立场性论文和教程。本综述首先介绍CDFSL的定义及其涉及的问题，然后提出核心科学问题与挑战。继而基于现有文献对经过验证的CDFSL方法进行系统综述，并依据严谨的分类体系给出详细描述。此外，本文概述并讨论了CDFSL在问题设定、应用和理论层面值得深入研究的几个有前景方向。