Episodic Training for Domain Generalization

TL;DR

This paper introduces an episodic training method for domain generalization that enhances model robustness to domain shifts, achieving state-of-the-art results and improving fixed feature extractors for downstream tasks.

Contribution

We propose an episodic training procedure that simulates domain shifts during training, leading to more robust models for domain generalization and improved feature extractors.

Findings

Achieves state-of-the-art performance on three DG benchmarks.

Improves robustness of fixed feature extractors on Visual Decathlon.

Training with episodic approach benefits standard computer vision practices.

Abstract

Domain generalization (DG) is the challenging and topical problem of learning models that generalize to novel testing domains with different statistics than a set of known training domains. The simple approach of aggregating data from all source domains and training a single deep neural network end-to-end on all the data provides a surprisingly strong baseline that surpasses many prior published methods. In this paper, we build on this strong baseline by designing an episodic training procedure that trains a single deep network in a way that exposes it to the domain shift that characterises a novel domain at runtime. Specifically, we decompose a deep network into feature extractor and classifier components, and then train each component by simulating it interacting with a partner who is badly tuned for the current domain. This makes both components more robust, ultimately leading to our networks producing state-of-the-art performance on three DG benchmarks. Furthermore, we consider the pervasive workflow of using an ImageNet trained CNN as a fixed feature extractor for downstream recognition tasks. Using the Visual Decathlon benchmark, we demonstrate that our episodic-DG training improves the performance of such a general-purpose feature extractor by explicitly training a feature for robustness to novel problems. This shows that DG training can benefit standard practice in computer vision.