Efﬁcient Generation of Complex Data Distributions

Kofman, Philipp

Домівка
→
Students Research & Project Works | Роботи студентів
→
Факультет прикладних наук
→
Освітня програма наук про дані
→
2020
→
Перегляд матеріалів

dc.contributor.author	Kofman, Philipp
dc.date.accessioned	2020-02-25T09:51:06Z
dc.date.available	2020-02-25T09:51:06Z
dc.date.issued	2020
dc.identifier.citation	Kofman, Philipp. Efﬁcient Generation of Complex Data Distributions : Master Thesis : manuscript / Philipp Kofman ; Supervisor Oles Dobosevych ; Ukrainian Catholic University, Department of Computer Sciences. – Lviv : [s.n.], 2020. – 33 p. : ill.	uk
dc.identifier.uri	http://er.ucu.edu.ua/handle/1/2048
dc.language.iso	en	uk
dc.subject	Efﬁcient Generatio	uk
dc.subject	Complex Data Distributions	uk
dc.subject	Style space analysis	uk
dc.title	Efﬁcient Generation of Complex Data Distributions	uk
dc.type	Preprint	uk
dc.status	Публікується вперше	uk
dc.description.abstracten	Currently, the active development of image processing methods requires large amounts of correctly labeled data. The lack of quality data makes it impossible to use various machine learning methods. In case of limited possibilities for collecting real data, used methods for their synthetic generation. In practice, we can formulate the task of the high-quality generation of synthetic images as an efﬁcient generation of complex data distributions, which is the object of study of this work. Generating high-quality synthetic data is an expensive and complicated process in terms of existing methods. We can distinguish two main approaches that are used to generate synthetic data: image generation based on rendered 3-D scenes and the use of GANs for simple images. These methods have some drawbacks, such as a narrow range of applicability and insufﬁcient distribution complexity of the obtained data. When using GANs to generate complex distributions, in practice, we face a visible increase in the complexity of the model architecture and training procedure. A deep understanding of the real data complex distributions can be used to improve the quality of synthetic generation. Minimizing the differences in the real and synthetic data distributions can improve not only the generation process but also develop tools for solving the problem of data lack in the ﬁeld of image processing.	uk