arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1710.03463cs.LG
收藏

学习泛化:面向领域泛化的元学习

Learning to Generalize: Meta-Learning for Domain Generalization

Queen Mary University of London(伦敦玛丽女王大学);University of Edinburgh(爱丁堡大学)

Da Li, Yongxin Yang, Yi-Zhe Song, Timothy M. Hospedales

摘要:

域偏移是指在一个源域中训练的模型在应用于具有不同统计数据的目标域时表现不佳的众所周知的问题。领域泛化(DG)技术试图通过产生模型来缓解这个问题,所述模型通过设计很好地泛化到新的测试领域。提出了一种新的领域泛化{元学习}方法。而不是设计一个特定的模型,是强大的域转移在大多数以前的DG工作,我们提出了一个模型不可知的训练过程DG。我们的算法模拟训练/测试域转移在训练过程中合成虚拟测试域内的每个小批量。元优化目标要求提高训练域性能的步骤也应该提高测试域性能。这个元学习过程训练具有良好泛化能力的模型到新的领域。我们评估了我们的方法,并在最近的跨域图像分类基准上取得了最先进的结果,同时在两个经典的强化学习任务上展示了其潜力。

英文摘要:

Domain shift refers to the well known problem that a model trained in one source domain performs poorly when applied to a target domain with different statistics. {Domain Generalization} (DG) techniques attempt to alleviate this issue by producing models which by design generalize well to novel testing domains. We propose a novel {meta-learning} method for domain generalization. Rather than designing a specific model that is robust to domain shift as in most previous DG work, we propose a model agnostic training procedure for DG. Our algorithm simulates train/test domain shift during training by synthesizing virtual testing domains within each mini-batch. The meta-optimization objective requires that steps to improve training domain performance should also improve testing domain performance. This meta-learning procedure trains models with good generalization ability to novel domains. We evaluate our method and achieve state of the art results on a recent cross-domain image classification benchmark, as well demonstrating its potential on two classic reinforcement learning tasks.

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。

↑