VarGFaceNet: An Efficient Variable Group Convolutional Neural Network for Lightweight Face Recognition

TL;DR

VarGFaceNet is a lightweight face recognition network that uses variable group convolution to balance computational efficiency and discriminative power, achieving high accuracy with fewer parameters.

Contribution

The paper introduces VarGFaceNet, a novel network employing variable group convolution, embedding optimization, and knowledge distillation to enhance lightweight face recognition performance.

Findings

Achieves competitive face recognition accuracy with reduced computational cost.

Effectively balances model complexity and discriminative ability.

Validated on DeepGlint-Light track of LFR 2019 challenge.

Abstract

To improve the discriminative and generalization ability of lightweight network for face recognition, we propose an efficient variable group convolutional network called VarGFaceNet. Variable group convolution is introduced by VarGNet to solve the conflict between small computational cost and the unbalance of computational intensity inside a block. We employ variable group convolution to design our network which can support large scale face identification while reduce computational cost and parameters. Specifically, we use a head setting to reserve essential information at the start of the network and propose a particular embedding setting to reduce parameters of fully-connected layer for embedding. To enhance interpretation ability, we employ an equivalence of angular distillation loss to guide our lightweight network and we apply recursive knowledge distillation to relieve the discrepancy between the teacher model and the student model. The champion of deepglint-light track of LFR (2019) challenge demonstrates the effectiveness of our model and approach. Implementation of VarGFaceNet will be released at https://github.com/zma-c-137/VarGFaceNet soon.