Domain generalisation (DG) methods address the problem of domain shift, when there is a mismatch between the distributions of training and target domains. Data augmentation approaches have emerged as a promising alternative for DG. However, data augmentation alone is not sufficient to achieve lower generalisation errors. This project proposes a new method that combines data augmentation and domain distance minimisation to address the problems associated with data augmentation and provide a guarantee on the learning performance, under an existing framework. Empirically, our method outperforms baseline results on DG benchmarks.
@article{arxiv.2012.13973,
title = {Domain Generalisation with Domain Augmented Supervised Contrastive Learning (Student Abstract)},
author = {Hoang Son Le and Rini Akmeliawati and Gustavo Carneiro},
journal= {arXiv preprint arXiv:2012.13973},
year = {2020}
}