Learning to Generalize: Meta-Learning for Domain Generalization

10 Oct 2017  ·  Da Li, Yongxin Yang, Yi-Zhe Song, Timothy M. Hospedales ·

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.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Domain Generalization PACS MLDG (Alexnet) Average Accuracy 70.01 # 89

Methods


No methods listed for this paper. Add relevant methods here