Адаптація контексту у задачах класифікації зображень
Loading...
Date
2021
Authors
Крошин, Олександр
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Rapid developments in the Deep Learning domain in recent years let researchers and practitioners shift their focus from training machine learning models itself to transferring the already-learnt knowledge and applying it in different applications. This paper discusses Domain Adaptation, a subdomain of transfer learning, primarily aimed at applying knowledge from a given source domain to an unknow target one. It discusses various Domain Adaptation settings under the context of Computer Vision, introduces self-ensembling Domain Adaptation methods for semi-supervised learning and illustrates its capabilities with proper experiments.
Experiments were implemented with Python 3.6 using libraries pytorch, numpy, pandas, opencv, matplotlib, torch-salad, etc.
Description
Keywords
адаптація, класифікація зображень, магістерська робота