Learning to Generalize: Meta-Learning for Domain Generalization


  • Da Li Queen Mary University of London
  • Yongxin Yang Queen Mary University of London
  • Yi-Zhe Song Queen Mary University of London
  • Timothy Hospedales The University of Edinburgh


Meta-Learning, Domain Generalization


Domain shift refers to the well known problem that a model trained in one source domain performs poorly when appliedto 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.




How to Cite

Li, D., Yang, Y., Song, Y.-Z., & Hospedales, T. (2018). Learning to Generalize: Meta-Learning for Domain Generalization. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11596