Domain Generalization by Rejecting Extreme Augmentations

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Aminbeidokhti, Masih, Peña, Fidel A. Guerrero, Medeiros, Heitor Rapela, Dubail, Thomas, Granger, Eric, Pedersoli, Marco
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911197893230592
author Aminbeidokhti, Masih
Peña, Fidel A. Guerrero
Medeiros, Heitor Rapela
Dubail, Thomas
Granger, Eric
Pedersoli, Marco
author_facet Aminbeidokhti, Masih
Peña, Fidel A. Guerrero
Medeiros, Heitor Rapela
Dubail, Thomas
Granger, Eric
Pedersoli, Marco
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2310_06670
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Domain Generalization by Rejecting Extreme Augmentations
Aminbeidokhti, Masih
Peña, Fidel A. Guerrero
Medeiros, Heitor Rapela
Dubail, Thomas
Granger, Eric
Pedersoli, Marco
Machine Learning
Computer Vision and Pattern Recognition
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
title Domain Generalization by Rejecting Extreme Augmentations
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2310.06670