TripleE: Easy Domain Generalization via Episodic Replay

TL;DR

TripleE introduces a simple yet effective domain generalization method using episodic replay and augmentation, focusing on subset learning and ensembling to improve performance on unseen domains.

Contribution

The paper proposes a novel domain generalization approach combining episodic replay and exhaustive augmentation, enhancing model diversity and data coverage during training.

Findings

Outperforms prior methods on six domain generalization benchmarks.

Simple augmentation and ensembling achieve significant improvements.

Focus on subset learning enhances generalization to unseen domains.

Abstract

Learning how to generalize the model to unseen domains is an important area of research. In this paper, we propose TripleE, and the main idea is to encourage the network to focus on training on subsets (learning with replay) and enlarge the data space in learning on subsets. Learning with replay contains two core designs, EReplayB and EReplayD, which conduct the replay schema on batch and dataset, respectively. Through this, the network can focus on learning with subsets instead of visiting the global set at a glance, enlarging the model diversity in ensembling. To enlarge the data space in learning on subsets, we verify that an exhaustive and singular augmentation (ESAug) performs surprisingly well on expanding the data space in subsets during replays. Our model dubbed TripleE is frustratingly easy, based on simple augmentation and ensembling. Without bells and whistles, our TripleE method surpasses prior arts on six domain generalization benchmarks, showing that this approach could serve as a stepping stone for future research in domain generalization.