TripleE: Easy Domain Generalization via Episodic Replay
It addresses the problem of generalizing models to unseen domains for machine learning practitioners, but it is incremental as it builds on existing replay and augmentation techniques.
The paper tackles domain generalization by proposing TripleE, a method that uses episodic replay with simple augmentation and ensembling to improve model diversity and data space, achieving state-of-the-art results on six benchmarks.
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.