arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.03757cs.LG
收藏

基于差异的领域自适应主动学习

Discrepancy-Based Active Learning for Domain Adaptation

Michelin(米其林);Centre Borelli, Université Paris-Saclay, CNRS, ENS Paris-Saclay(巴黎萨克雷大学博雷利中心、法国国家科学研究中心、巴黎萨克雷高等师范学院);ENSIIE(法国国家信息与自动化高等工程师学院)

Antoine de Mathelin, Francois Deheeger, Mathilde Mougeot, Nicolas Vayatis

摘要:

本文的目标是设计主动学习策略,导致领域自适应的假设下,Lipschitz函数。在Mansour et al.(2009)以前的工作的基础上,我们采用了源和目标分布之间差异距离的概念,将假设类的最大化限制在对源域执行准确标记的局部函数类上。我们推导出的泛化误差界等主动学习策略的Rademacher平均和本地化的差异一般损失函数,满足正则性条件。从理论界出发,推导出了一种适用于大数据集情况的实用K中心点算法。我们的数值实验表明,该算法是竞争力对其他国家的最先进的主动学习技术的背景下,领域自适应,特别是对大数据集的约10万幅图像。

英文摘要:

The goal of the paper is to design active learning strategies which lead to domain adaptation under an assumption of Lipschitz functions. Building on previous work by Mansour et al. (2009) we adapt the concept of discrepancy distance between source and target distributions to restrict the maximization over the hypothesis class to a localized class of functions which are performing accurate labeling on the source domain. We derive generalization error bounds for such active learning strategies in terms of Rademacher average and localized discrepancy for general loss functions which satisfy a regularity condition. A practical K-medoids algorithm that can address the case of large data set is inferred from the theoretical bounds. Our numerical experiments show that the proposed algorithm is competitive against other state-of-the-art active learning techniques in the context of domain adaptation, in particular on large data sets of around one hundred thousand images.

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。

↑