University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Learning to generalize: Meta-learning for domain generalization

Li, D., Yang, Y., Song, Yi-Zhe and Hospedales, T.M. (2018) Learning to generalize: Meta-learning for domain generalization In: Thirty-Second AAAI Conference on Artificial Intelligence (AAAI 2018), 02-07 Feb 2018, Hilton New Orleans Riverside Hotel, New Orleans, Louisiana, USA.

Full text not available from this repository.


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.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
Li, D.
Yang, Y.
Hospedales, T.M.
Date : 29 April 2018
Related URLs :
Depositing User : Clive Harris
Date Deposited : 03 Jul 2019 14:00
Last Modified : 03 Jul 2019 14:00

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800