A Novel Cross-Perturbation for Single Domain Generalization

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhao, Dongjia, Qi, Lei, Shi, Xiao, Shi, Yinghuan, Geng, Xin
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917687126392832
author Zhao, Dongjia
Qi, Lei
Shi, Xiao
Shi, Yinghuan
Geng, Xin
author_facet Zhao, Dongjia
Qi, Lei
Shi, Xiao
Shi, Yinghuan
Geng, Xin
contents Single domain generalization aims to enhance the ability of the model to generalize to unknown domains when trained on a single source domain. However, the limited diversity in the training data hampers the learning of domain-invariant features, resulting in compromised generalization performance. To address this, data perturbation (augmentation) has emerged as a crucial method to increase data diversity. Nevertheless, existing perturbation methods often focus on either image-level or feature-level perturbations independently, neglecting their synergistic effects. To overcome these limitations, we propose CPerb, a simple yet effective cross-perturbation method. Specifically, CPerb utilizes both horizontal and vertical operations. Horizontally, it applies image-level and feature-level perturbations to enhance the diversity of the training data, mitigating the issue of limited diversity in single-source domains. Vertically, it introduces multi-route perturbation to learn domain-invariant features from different perspectives of samples with the same semantic category, thereby enhancing the generalization capability of the model. Additionally, we propose MixPatch, a novel feature-level perturbation method that exploits local image style information to further diversify the training data. Extensive experiments on various benchmark datasets validate the effectiveness of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2308_00918
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Novel Cross-Perturbation for Single Domain Generalization
Zhao, Dongjia
Qi, Lei
Shi, Xiao
Shi, Yinghuan
Geng, Xin
Computer Vision and Pattern Recognition
Single domain generalization aims to enhance the ability of the model to generalize to unknown domains when trained on a single source domain. However, the limited diversity in the training data hampers the learning of domain-invariant features, resulting in compromised generalization performance. To address this, data perturbation (augmentation) has emerged as a crucial method to increase data diversity. Nevertheless, existing perturbation methods often focus on either image-level or feature-level perturbations independently, neglecting their synergistic effects. To overcome these limitations, we propose CPerb, a simple yet effective cross-perturbation method. Specifically, CPerb utilizes both horizontal and vertical operations. Horizontally, it applies image-level and feature-level perturbations to enhance the diversity of the training data, mitigating the issue of limited diversity in single-source domains. Vertically, it introduces multi-route perturbation to learn domain-invariant features from different perspectives of samples with the same semantic category, thereby enhancing the generalization capability of the model. Additionally, we propose MixPatch, a novel feature-level perturbation method that exploits local image style information to further diversify the training data. Extensive experiments on various benchmark datasets validate the effectiveness of our method.
title A Novel Cross-Perturbation for Single Domain Generalization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2308.00918