Projects per year
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.
|Title of host publication||AAAI Conference on Artificial Intelligence (AAAI 2018)|
|Number of pages||8|
|Publication status||E-pub ahead of print - 7 Feb 2018|
|Event||Thirty-Second AAAI Conference on Artificial Intelligence - Hilton New Orleans Riverside, New Orleans, United States|
Duration: 2 Feb 2018 → 7 Feb 2018
|Conference||Thirty-Second AAAI Conference on Artificial Intelligence|
|Abbreviated title||AAAI 2018|
|Period||2/02/18 → 7/02/18|
FingerprintDive into the research topics of 'Learning to Generalize: Meta-Learning for Domain Generalization'. Together they form a unique fingerprint.
- 1 Finished
DREAM - Deferred Restructuring of Experience in Autonomous Machines
1/09/16 → 31/12/18