Federated Learning for Face Recognition via Intra-subject Self-supervised Learning

TL;DR

This paper introduces FedFS, a federated learning framework that enhances personalized face recognition by integrating intra-subject self-supervised learning and adaptive label construction, improving model robustness and privacy.

Contribution

The paper proposes a novel federated learning architecture, FedFS, that incorporates intra-subject self-supervised learning and adaptive label reformulation for personalized face recognition.

Findings

FedFS outperforms previous methods on DigiFace-1M and VGGFace datasets.

The framework effectively leverages local and global features for improved recognition.

Regularization prevents overfitting and stabilizes training.

Abstract

Federated Learning (FL) for face recognition aggregates locally optimized models from individual clients to construct a generalized face recognition model. However, previous studies present two major challenges: insufficient incorporation of self-supervised learning and the necessity for clients to accommodate multiple subjects. To tackle these limitations, we propose FedFS (Federated Learning for personalized Face recognition via intra-subject Self-supervised learning framework), a novel federated learning architecture tailored to train personalized face recognition models without imposing subjects. Our proposed FedFS comprises two crucial components that leverage aggregated features of the local and global models to cooperate with representations of an off-the-shelf model. These components are (1) adaptive soft label construction, utilizing dot product operations to reformat labels within intra-instances, and (2) intra-subject self-supervised learning, employing cosine similarity operations to strengthen robust intra-subject representations. Additionally, we introduce a regularization loss to prevent overfitting and ensure the stability of the optimized model. To assess the effectiveness of FedFS, we conduct comprehensive experiments on the DigiFace-1M and VGGFace datasets, demonstrating superior performance compared to previous methods.