Domain Adaptation Methods for Image Processing

Student: Volodkevich Anna

Supervisor: Stanislav N. Fedotov

Educational Programme: Data Science (Master)

Final Grade: 8

Year of Graduation: 2020

The work considers approaches to unsupervised domain adaptation for image processing. Domain adaptation methods could be used for classification and segmentation tasks, nearest images search, image generation. Unsupervised domain adaptation is characterized by the presence of labeled source domain data and unlabeled target domain data. Domain adaptation methods are used to label target domain data using labeled source domain data and available target data. The work contains an overview of modern methods of unsupervised domain adaptation for image classification tasks and experiments on implementation and improvement of selected methods.

Full text (added May 25, 2020)

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