Domain Generalization via Model-Agnostic Learning of Semantic Features

TL;DR

This paper proposes a model-agnostic meta-learning approach with semantic feature regularization to improve domain generalization, achieving state-of-the-art results on object recognition and medical segmentation tasks.

Contribution

It introduces a novel combination of gradient-based meta-learning and semantic feature regularization for better domain generalization.

Findings

Achieved state-of-the-art results on object recognition benchmarks.

Demonstrated consistent improvements on medical image segmentation.

Validated effectiveness of semantic regularization losses.

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.