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

2020/12/27 by Le, Hoang Son, Akmeliawati, Rini, Carneiro, Gustavo
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2012.13973

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.

Related

• Connecting Domains and Contrasting Samples: A Ladder for Domain Generalization
• Incorporating Supervised Domain Generalization into Data Augmentation
• Untapped Potential of Data Augmentation: A Domain Generalization Viewpoint
• FixCLR: Negative-Class Contrastive Learning for Semi-Supervised Domain Generalization
• Rethinking Domain Generalization Baselines