FedFace: Collaborative Learning of Face Recognition Model

TL;DR

FedFace introduces a federated learning framework that enables collaborative training of face recognition models across multiple clients while preserving privacy, achieving improved verification performance without sharing raw face data.

Contribution

The paper presents FedFace, a novel federated learning approach tailored for face recognition that maintains privacy by keeping face data on local devices and only sharing model updates.

Findings

Enhanced face verification accuracy on LFW, IJB-A, and IJB-C benchmarks.

Effective privacy-preserving collaborative learning for face recognition.

Outperforms baseline models trained without federated learning.

Abstract

DNN-based face recognition models require large centrally aggregated face datasets for training. However, due to the growing data privacy concerns and legal restrictions, accessing and sharing face datasets has become exceedingly difficult. We propose FedFace, a federated learning (FL) framework for collaborative learning of face recognition models in a privacy-aware manner. FedFace utilizes the face images available on multiple clients to learn an accurate and generalizable face recognition model where the face images stored at each client are neither shared with other clients nor the central host and each client is a mobile device containing face images pertaining to only the owner of the device (one identity per client). Our experiments show the effectiveness of FedFace in enhancing the verification performance of pre-trained face recognition system on standard face verification benchmarks namely LFW, IJB-A, and IJB-C.