• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Image-text Matching Only with Transformer-like Architecture

Student: Pleshkova Alina

Supervisor: Boris Novikov

Faculty: St. Petersburg School of Physics, Mathematics, and Computer Science

Educational Programme: Enterprise Software Development (Master)

Final Grade: 9

Year of Graduation: 2021

With the development of technology, people increasingly have to work with multimedia content. With the advent of multimedia data, the problem of linking information of different types appears. One such problem is text-to-image matching. The solution of this problem is very important in text-visual search. Recently, the ViLT model has emerged, which is the SOTA among the models for the task of text and image matching. The work is devoted to adapting this model for training on a small dataset and with a small batch size.

Full text (added May 21, 2021)

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