This article is cited in 2 papers

Topical issue

Distilling face recognition models trained using margin-based softmax function

D. V. Svitov^ab, S. A. Alyamkin<sup>a

a</sup> Expasoft LLC, Novosibirsk, 630090 Russia
^b Institute of Automation and Electrometry of the Siberian Branch of the Russian Academy of Sciences, Novosibirsk, 630090 Russia

Abstract: The use of convolutional neural networks trained with the margin-based softmax function allows achieving the highest accuracy in the face recognition problem. The development of embedded systems such as smart intercoms has increased interest in lightweight neural networks. Thus, lightweight neural network models, trained using the margin-based softmax function, were proposed for the face identification problem. In the present paper, we propose a distillation method that allows obtaining greater accuracy than other methods for the face recognition problem on LFW, AgeDB-30, and Megaface datasets. The main idea of our approach is to use the class centers of the teacher network to initialize the student network. Then the student network is trained to produce biometric vectors the angles from which to the class centers are equal to the angles in the teacher network.

Keywords: convolutional neural network, distillation, bioidentification.

Presented by the member of Editorial Board: A. A. Lazarev

Received: 10.01.2022
Revised: 08.05.2022
Accepted: 29.06.2022

DOI: 10.31857/S000523102210004X

 English version: Automation and Remote Control, 2022, 83:10, 1517–1526