MarginDistillation: distillation for margin-based softmax

TL;DR

This paper introduces MarginDistillation, a novel knowledge distillation method that leverages class centers from a teacher network to improve lightweight face recognition models with margin-based softmax.

Contribution

The paper proposes a new distillation technique using class centers to enhance lightweight neural networks for face recognition with margin softmax.

Findings

Outperforms existing distillation methods on LFW, AgeDB-30, Megaface datasets.

Effective in training lightweight models for edge device deployment.

Improves face recognition accuracy with margin-based softmax.

Abstract

The usage of convolutional neural networks (CNNs) in conjunction with a margin-based softmax approach demonstrates a state-of-the-art performance for the face recognition problem. Recently, lightweight neural network models trained with the margin-based softmax have been introduced for the face identification task for edge devices. In this paper, we propose a novel distillation method for lightweight neural network architectures that outperforms other known methods for the face recognition task on LFW, AgeDB-30 and Megaface datasets. The idea of the proposed method is to use class centers from the teacher network for the student network. Then the student network is trained to get the same angles between the class centers and the face embeddings, predicted by the teacher network.