English

Domain Generalisation with Domain Augmented Supervised Contrastive Learning (Student Abstract)

Machine Learning 2020-12-29 v1 Computer Vision and Pattern Recognition

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-23T21:27:38.997Z