QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit Quantization

TL;DR

QuantFace leverages low-bit quantization and synthetic data to create lightweight, privacy-preserving face recognition models that maintain high accuracy while significantly reducing computational costs.

Contribution

This work introduces a novel low-bit quantization method using synthetic data, eliminating the need for real training data or specialized architectures in face recognition.

Findings

Model size reduced up to 5x

Maintains high verification accuracy

Effective across multiple benchmarks and architectures

Abstract

Deep learning-based face recognition models follow the common trend in deep neural networks by utilizing full-precision floating-point networks with high computational costs. Deploying such networks in use-cases constrained by computational requirements is often infeasible due to the large memory required by the full-precision model. Previous compact face recognition approaches proposed to design special compact architectures and train them from scratch using real training data, which may not be available in a real-world scenario due to privacy concerns. We present in this work the QuantFace solution based on low-bit precision format model quantization. QuantFace reduces the required computational cost of the existing face recognition models without the need for designing a particular architecture or accessing real training data. QuantFace introduces privacy-friendly synthetic face data to the quantization process to mitigate potential privacy concerns and issues related to the accessibility to real training data. Through extensive evaluation experiments on seven benchmarks and four network architectures, we demonstrate that QuantFace can successfully reduce the model size up to 5x while maintaining, to a large degree, the verification performance of the full-precision model without accessing real training datasets.