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.
In this paper, we tackle the problem of domain generalization: how to learn a generalized feature representation for an "unseen" target domain by taking the advantage of multipl...
The most successful 2D object detection methods require a large number of images annotated with object bounding boxes to be collected for training. We present an alternative app...
We propose a novel context-dependent (CD) model for large-vocabulary speech recognition (LVSR) that leverages recent advances in using deep belief networks for phone recognition...
Delayed reinforcement learning is an attractive framework for the unsupervised learning of action policies for autonomous agents. Some existing delayed reinforcement learning te...
The exponential increase in the availability of online reviews and recommendations makes sentiment classification an interesting topic in academic and industrial research. Revie...
Social media, news, blog, policy document mentions