Saved in:
Bibliographic Details
Main Authors: Wei, Yikang, Han, Yahong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.10272
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910302581293056
author Wei, Yikang
Han, Yahong
author_facet Wei, Yikang
Han, Yahong
contents Federated Domain Generalization aims to learn a domain-invariant model from multiple decentralized source domains for deployment on unseen target domain. Due to privacy concerns, the data from different source domains are kept isolated, which poses challenges in bridging the domain gap. To address this issue, we propose a Multi-source Collaborative Gradient Discrepancy Minimization (MCGDM) method for federated domain generalization. Specifically, we propose intra-domain gradient matching between the original images and augmented images to avoid overfitting the domain-specific information within isolated domains. Additionally, we propose inter-domain gradient matching with the collaboration of other domains, which can further reduce the domain shift across decentralized domains. Combining intra-domain and inter-domain gradient matching, our method enables the learned model to generalize well on unseen domains. Furthermore, our method can be extended to the federated domain adaptation task by fine-tuning the target model on the pseudo-labeled target domain. The extensive experiments on federated domain generalization and adaptation indicate that our method outperforms the state-of-the-art methods significantly.
format Preprint
id arxiv_https___arxiv_org_abs_2401_10272
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Source Collaborative Gradient Discrepancy Minimization for Federated Domain Generalization
Wei, Yikang
Han, Yahong
Computer Vision and Pattern Recognition
Artificial Intelligence
Federated Domain Generalization aims to learn a domain-invariant model from multiple decentralized source domains for deployment on unseen target domain. Due to privacy concerns, the data from different source domains are kept isolated, which poses challenges in bridging the domain gap. To address this issue, we propose a Multi-source Collaborative Gradient Discrepancy Minimization (MCGDM) method for federated domain generalization. Specifically, we propose intra-domain gradient matching between the original images and augmented images to avoid overfitting the domain-specific information within isolated domains. Additionally, we propose inter-domain gradient matching with the collaboration of other domains, which can further reduce the domain shift across decentralized domains. Combining intra-domain and inter-domain gradient matching, our method enables the learned model to generalize well on unseen domains. Furthermore, our method can be extended to the federated domain adaptation task by fine-tuning the target model on the pseudo-labeled target domain. The extensive experiments on federated domain generalization and adaptation indicate that our method outperforms the state-of-the-art methods significantly.
title Multi-Source Collaborative Gradient Discrepancy Minimization for Federated Domain Generalization
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2401.10272