Face Recognition Using the Transformer Architecture

Student: Tya-shen-tin Yegor

Supervisor: Sergey Lisitsyn

Educational Programme: Big Data Systems (Master)

Year of Graduation: 2021

There are many problems in biology, safety, and traffic that deep learning and computer vision can solve. In 2017, Google researchers developed the Transformer architecture and described how it works in the article "Attention is all you need". In 2020, Google Brain researchers developed an architecture that directly relates the Transformer architecture to image data. In this master thesis, we use the Transformer neural network architecture to solve the problem of face recognition, as well as compare the performance and efficiency of this method with existing state-of-the-art analogs.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses