Domain Generalization: A Survey. (arXiv:2103.02503v5 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2103.02503

Generalization to out-of-distribution (OOD) data is a capability natural to
humans yet challenging for machines to reproduce. This is because most learning
algorithms strongly rely on the i.i.d.~assumption on source/target data, which
is often violated in practice due to domain shift. Domain generalization (DG)
aims to achieve OOD generalization by using only source data for model
learning. Over the last ten years, research in DG has made great progress,
leading to a broad spectrum of methodologies, e.g., those based on …

arxiv survey