BriefGPT.xyz
Mar, 2020
学习单域通用性
Learning to Learn Single Domain Generalization
HTML
PDF
Fengchun Qiao, Long Zhao, Xi Peng
TL;DR
本篇文章介绍了一种名为对抗域增强的方法,用于在单一训练域情况下提高模型的泛化性能,通过使用元学习方案和WAE来松弛最坏情况限制,并在多个基准数据集上广泛实验,验证了该方法对于缓解单一域泛化问题的优越表现。
Abstract
We are concerned with a worst-case scenario in
model generalization
, in the sense that a model aims to perform well on many unseen domains while there is only one single domain available for training. We propose a new method named
→