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

Authors

  • Hoang Son Le The University of Adelaide
  • Rini Akmeliawati The University of Adelaide
  • Gustavo Carneiro The University of Adelaide

Keywords:

Domain Generalisation, Data Augmentation, Non-i.i.d Setting

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.

Downloads

Published

2021-05-18

How to Cite

Le, H. S., Akmeliawati, R., & Carneiro, G. (2021). Domain Generalisation with Domain Augmented Supervised Contrastive Learning (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15821-15822. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17907

Issue

Section

AAAI Student Abstract and Poster Program