Federated Unsupervised Domain Adaptation for Face Recognition

by   Weiming Zhuang, et al.
SenseTime Corporation
Nanyang Technological University

Given labeled data in a source domain, unsupervised domain adaptation has been widely adopted to generalize models for unlabeled data in a target domain, whose data distributions are different. However, existing works are inapplicable to face recognition under privacy constraints because they require sharing of sensitive face images between domains. To address this problem, we propose federated unsupervised domain adaptation for face recognition, FedFR. FedFR jointly optimizes clustering-based domain adaptation and federated learning to elevate performance on the target domain. Specifically, for unlabeled data in the target domain, we enhance a clustering algorithm with distance constrain to improve the quality of predicted pseudo labels. Besides, we propose a new domain constraint loss (DCL) to regularize source domain training in federated learning. Extensive experiments on a newly constructed benchmark demonstrate that FedFR outperforms the baseline and classic methods on the target domain by 3


page 1

page 2


Towards Unsupervised Domain Adaptation for Deep Face Recognition under Privacy Constraints via Federated Learning

Unsupervised domain adaptation has been widely adopted to generalize mod...

Cluster-Guided Unsupervised Domain Adaptation for Deep Speaker Embedding

Recent studies have shown that pseudo labels can contribute to unsupervi...

Adaptive Face Recognition Using Adversarial Information Network

In many real-world applications, face recognition models often degenerat...

Deep face recognition with clustering based domain adaptation

Despite great progress in face recognition tasks achieved by deep convol...

Federated Adversarial Domain Adaptation

Federated learning improves data privacy and efficiency in machine learn...

Unsupervised Domain Adaptation for Device-free Gesture Recognition

Device free human gesture recognition with Radio Frequency signals has a...

Domain adaptation for person re-identification on new unlabeled data using AlignedReID++

In the world where big data reigns and there is plenty of hardware prepa...

Please sign up or login with your details

Forgot password? Click here to reset