Development of Domain Adaptation Methods for Generative Models (GANs, diffusion)

Student: Korolev Kirill

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Final Grade: 9

Year of Graduation: 2024

Modern generative adversarial networks (GANs) enable the synthesis of high-quality images and provide tools for fine-grained image manipulation. However, out-of-domain generation requires an additional fine-tuning of a generator or non-flexible latent optimization, which requires training for each new image. A novel encoder, which learns offsets in a $\mathcal{S}$ space and allows a GAN generator to adapt to a new domain in a single pass, is proposed and implemented. An ablation study of loss components and usage of projection embeddings is conducted. A method for regularization in a multi-domain setting is proposed. A thorough comparison with prior domain adaptation methods is made.

Full text (added May 20, 2024)

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