Keywords: domain generalization, semi-supervised learning, pseudo-labeling, stochastic neural network, stylization
TL;DR: We address semi-supervised domain generalization with pseudo-labeling, stochastic classifier, and multi-view consistency learning.
Abstract: We study semi-supervised domain generalization (SSDG), a more realistic problem setting than existing domain generalization research. In particular, SSDG assumes only a few data are labeled from each source domain, along with abundant unlabeled data. Our proposed approach, called StyleMatch, extends FixMatch's two-view consistency learning paradigm in two crucial ways to address SSDG: first, stochastic modeling is applied to the classifier's weights to mitigate overfitting in the scarce labeled data; and second, style augmentation is integrated as a third view into the multi-view consistency learning framework to enhance robustness to domain shift. Two SSDG benchmarks are established where StyleMatch outperforms strong baseline methods developed in relevant areas including domain generalization and semi-supervised learning.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 2 code implementations](https://www.catalyzex.com/paper/arxiv:2106.00592/code)