Learning to Generalize: Meta-Learning for Domain Generalization

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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.
Original languageEnglish
Title of host publicationAAAI Conference on Artificial Intelligence (AAAI 2018)
Number of pages8
ISBN (Electronic)978-1-57735-800-8
Publication statusE-pub ahead of print - 7 Feb 2018
EventThirty-Second AAAI Conference on Artificial Intelligence - Hilton New Orleans Riverside, New Orleans, United States
Duration: 2 Feb 20187 Feb 2018
https://aaai.org/Conferences/AAAI-18/
https://aaai.org/Conferences/AAAI-18/

Publication series

Name
PublisherAAAI
ISSN (Electronic)2374-3468

Conference

ConferenceThirty-Second AAAI Conference on Artificial Intelligence
Abbreviated titleAAAI 2018
Country/TerritoryUnited States
CityNew Orleans
Period2/02/187/02/18
Internet address

Fingerprint

Dive into the research topics of 'Learning to Generalize: Meta-Learning for Domain Generalization'. Together they form a unique fingerprint.

Cite this