Few-Shot Learning for Online Large Scale Fine-Grained Image Recognition

dc.contributor.advisorTereshchenko Vasily Mykolayovych
dc.contributor.authorHolubakha Mykyta Ihorovich
dc.date.accessioned2023-03-29T12:53:50Z
dc.date.available2023-03-29T12:53:50Z
dc.date.issued2021
dc.description.abstractIn this work we have analyzed the existing body of research on few-shot learning and the various methods used to solve the few-shot image classification problem. We have treated, both theoretically and experimentally, embedding learning methods, multitask methods, different kinds of metric losses. Tried various self- and semi-supervised learning methods like MoCo, SwAV, SimCLR, BYOL and SimSiam. In addition, we have tackled the problem of performing online large-slace image recognition. It requires solving tasks like Out-Of-Distribution detection and clusterization, class discovery. As a result of this work, we have proposed a mechanism for implementing a system to solve the problem of fine-grained large-scale image recognition using few-shot learning methods. We have conducted thourough qualitative and quantitative analysis on the application of various few-shot learning methods for image classification implemented in PyTorch both in benchmark and real-world data. This methods will further be improved on and tested on real-world product data.uk_UA
dc.identifier.citationHolubakha M. I. Few-Shot Learning for Online Large Scale Fine-Grained Image Recognition : qualification work ... master’s : 122 Computer Science / Holubakha Mykyta Ihorovich. - Kyiv, 2021. - 58 p.uk_UA
dc.identifier.urihttps://ir.library.knu.ua/handle/123456789/2977
dc.language.isoenuk_UA
dc.subject12 Інформаційні технологіїuk_UA
dc.subject122 Комп’ютерні наукиuk_UA
dc.titleFew-Shot Learning for Online Large Scale Fine-Grained Image Recognitionuk_UA
science.typeМагістерські роботиuk_UA
Файли
Контейнер Original
Зараз відображається 1 - 1 з 1
Завантаження...
Ескіз
Назва:
Holubakha_mahistr.pdf
Розмір:
2.09 MB
Формат:
Adobe Portable Document Format
Опис:
магістерська робота