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:为了解决这个问题,我们提议了少见的学习(FSL),但假定所有样本(包括源和目标任务数据,其目标任务由来源和任务数据事先知情进行)都来自同一领域,这是现实世界中的一种严格假设。为了减轻这一限制,跨领域少见学习(CDFSL)获得了关注,因为它允许不同领域和标签空间提供源和目标数据。本文件首次对CDFSL进行了全面审查,由于FSL的独特设置和困难,它得到的关注远远少于FSL。我们期望这份文件既作为立场文件,又作为在CDFSL进行研究的参与者的辅导员。这一审查首先介绍了CDFSL的定义和所涉问题,随后是核心科学问题和挑战。随后,对现有文献中经过验证的CDFSL方法进行了全面审查,并根据严格的分类作了详细描述。此外,本文件的大纲和讨论CDFSL的一些很有希望的理论方向,这些理论涉及值得进一步调查的问题。</s>