Domain Generalization by Rejecting Extreme Augmentations
Abstract
Data augmentation is one of the most effective techniques for regularizing deep learning models and improving their recognition performance in a variety of tasks and domains. However, this holds for standard in-domain settings, in which the training and test data follow the same distribution. For the out-of-domain case, where the test data follow a different and unknown distribution, the best recipe for data augmentation is unclear. In this paper, we show that for out-of-domain and domain generalization settings, data augmentation can provide a conspicuous and robust improvement in performance. To do that, we propose a simple training procedure: (i) use uniform sampling on standard data augmentation transformations; (ii) increase the strength transformations to account for the higher data variance expected when working out-of-domain, and (iii) devise a new reward function to reject extreme transformations that can harm the training. With this procedure, our data augmentation scheme achieves a level of accuracy that is comparable to or better than state-of-the-art methods on benchmark domain generalization datasets. Code: https://github.com/Masseeh/DCAug
Cite
@article{arxiv.2310.06670,
title = {Domain Generalization by Rejecting Extreme Augmentations},
author = {Masih Aminbeidokhti and Fidel A. Guerrero Peña and Heitor Rapela Medeiros and Thomas Dubail and Eric Granger and Marco Pedersoli},
journal= {arXiv preprint arXiv:2310.06670},
year = {2025}
}
Comments
WACV 2024: Winter Conference on Applications of Computer Vision 2024