Published on Tue Oct 29 2019

Domain Generalization via Model-Agnostic Learning of Semantic Features

Qi Dou, Daniel C. Castro, Konstantinos Kamnitsas, Ben Glocker

Generalization capability to unseen domains is crucial for machine learning models. We adopt a model-agnostic learning paradigm with gradient-based meta-train and meta-test procedures. Globally, we promote domain-independent class-specific cohesion and separation of sample features with a metric-learning component.

0
0
0
Abstract

Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions. We investigate the challenging problem of domain generalization, i.e., training a model on multi-domain source data such that it can directly generalize to target domains with unknown statistics. We adopt a model-agnostic learning paradigm with gradient-based meta-train and meta-test procedures to expose the optimization to domain shift. Further, we introduce two complementary losses which explicitly regularize the semantic structure of the feature space. Globally, we align a derived soft confusion matrix to preserve general knowledge about inter-class relationships. Locally, we promote domain-independent class-specific cohesion and separation of sample features with a metric-learning component. The effectiveness of our method is demonstrated with new state-of-the-art results on two common object recognition benchmarks. Our method also shows consistent improvement on a medical image segmentation task.