Open AccessDATA AUGMENTATION METHOD USING GENERATIVE ADVERSARIAL NETWORKS
Author(s) -
Oleksandr Chaikovskyi,
Artem Volokyta,
Артемій КИР’ЯНОВ,
Heorhii Loutskii
Publication year - 2021
Publication title -
tehnìčnì nauki ta tehnologìï
Language(s) - English
Resource type - Journals
eISSN - 2519-4569
pISSN - 2411-5363
DOI - 10.25140/2411-5363-2021-2(24)-83-91
Subject(s) - adversarial system , generative grammar , computer science , generative adversarial network , image (mathematics) , convolutional neural network , artificial intelligence , pattern recognition (psychology) , machine learning
The article discusses a data augmentation method based on generative adversarial networks to improve the accuracy of image classification by convolutional neural networks. A comparative analysis of the proposed method with classical image augmentation methods was performed.