arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.02785cs.LGcs.AIcs.CVcs.NE
收藏

通过元学习实现领域泛化:一项综述

Domain Generalization through Meta-Learning: A Survey

Chalmers University of Technology(查尔姆斯理工大学)

Arsham Gholamzadeh Khoee, Yinan Yu, Robert Feldt

AI总结:

本综述探讨了元学习在解决深度神经网络分布外泛化问题中的应用,基于特征提取与分类器学习方法提出新分类法与决策图,为领域泛化模型的选择与开发提供系统指导。

摘要:

深度神经网络(DNNs)彻底改变了人工智能,但在面对分布外(OOD)数据时往往性能不佳。由于现实应用中不可避免的领域偏移,这是一种常见情况。这一局限性源于训练和测试数据共享相同分布的常见假设——该假设在实践中经常被打破。尽管 DNNs 在海量数据和计算能力下表现出色,但它们在应对分布偏移和有限标注数据时仍面临困难,导致过拟合及在多种任务和领域间泛化能力差。元学习提供了一种极具前景的方法,通过采用能在多种任务间获取可迁移知识以实现快速适应的算法,免除了从头学习每项任务的需求。本综述深入探讨元学习领域,重点关注其对领域泛化的贡献。我们首先阐明了用于领域泛化的元学习概念,并基于特征提取策略和分类器学习方法引入了一种新颖的分类法,提供了方法论的细粒度视角。此外,我们提出了一幅决策图,以协助读者根据数据可用性和领域偏移在分类法中进行导航,使其能够选择并开发适合特定问题需求的恰当模型。通过对现有方法和基础理论的详尽回顾,我们勾勒出了该领域的基本框架。本综述提供了实用见解,并对极具前景的研究方向进行了有根据的讨论。

英文摘要:

Deep neural networks (DNNs) have revolutionized artificial intelligence but often lack performance when faced with out-of-distribution (OOD) data, a common scenario due to the inevitable domain shifts in real-world applications. This limitation stems from the common assumption that training and testing data share the same distribution--an assumption frequently violated in practice. Despite their effectiveness with large amounts of data and computational power, DNNs struggle with distributional shifts and limited labeled data, leading to overfitting and poor generalization across various tasks and domains. Meta-learning presents a promising approach by employing algorithms that acquire transferable knowledge across various tasks for fast adaptation, eliminating the need to learn each task from scratch. This survey paper delves into the realm of meta-learning with a focus on its contribution to domain generalization. We first clarify the concept of meta-learning for domain generalization and introduce a novel taxonomy based on the feature extraction strategy and the classifier learning methodology, offering a granular view of methodologies. Additionally, we present a decision graph to assist readers in navigating the taxonomy based on data availability and domain shifts, enabling them to select and develop a proper model tailored to their specific problem requirements. Through an exhaustive review of existing methods and underlying theories, we map out the fundamentals of the field. Our survey provides practical insights and an informed discussion on promising 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。

↑