Learning to Generalize: Meta-Learning for Domain Generalization

Code

• github.com/thuml/Transfer-Learning-Library
  pytorch★ 3,889
• github.com/facebookresearch/DomainBed
  pytorch★ 1,604
• github.com/HAHA-DL/MLDG
  pytorch★ 151
• github.com/Pulkit-Khandelwal/medical-mldg-seg
  pytorch★ 33
• github.com/Pulkit-Khandelwal/mldg
  pytorch★ 0

Abstract

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.

Tasks

Benchmark Results

Reproductions