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

by   Weiming Zhuang, et al.

Unsupervised domain adaptation has been widely adopted to generalize models for unlabeled data in a target domain, given labeled data in a source domain, whose data distributions differ from the target domain. However, existing works are inapplicable to face recognition under privacy constraints because they require sharing sensitive face images between two domains. To address this problem, we propose a novel unsupervised federated face recognition approach (FedFR). FedFR improves the performance in the target domain by iteratively aggregating knowledge from the source domain through federated learning. It protects data privacy by transferring models instead of raw data between domains. Besides, we propose a new domain constraint loss (DCL) to regularize source domain training. DCL suppresses the data volume dominance of the source domain. We also enhance a hierarchical clustering algorithm to predict pseudo labels for the unlabeled target domain accurately. To this end, FedFR forms an end-to-end training pipeline: (1) pre-train in the source domain; (2) predict pseudo labels by clustering in the target domain; (3) conduct domain-constrained federated learning across two domains. Extensive experiments and analysis on two newly constructed benchmarks demonstrate the effectiveness of FedFR. It outperforms the baseline and classic methods in the target domain by over 4 light on applying federated learning to more computer vision tasks under privacy constraints.


page 1

page 3


Federated Unsupervised Domain Adaptation for Face Recognition

Given labeled data in a source domain, unsupervised domain adaptation ha...

Unsupervised Domain Adaptation Through Transferring both the Source-Knowledge and Target-Relatedness Simultaneously

Unsupervised domain adaptation (UDA) is an emerging research topic in th...

Adaptive Face Recognition Using Adversarial Information Network

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

A Prototype-Oriented Clustering for Domain Shift with Source Privacy

Unsupervised clustering under domain shift (UCDS) studies how to transfe...

Multi-Source Domain Adaptation Based on Federated Knowledge Alignment

Federated Learning (FL) facilitates distributed model learning to protec...

Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the OR

The fine-grained localization of clinicians in the operating room (OR) i...

Maximizing Model Generalization for Manufacturing with Self-Supervised Learning and Federated Learning

Deep Learning (DL) can diagnose faults and assess machine health from ra...

Please sign up or login with your details

Forgot password? Click here to reset