Публікація:
CLIPTraVeLGAN for Semantically Robust Unpaired Image Translation

dc.contributor.authorBodyanskiy, Y.
dc.contributor.authorRyabova, N.
dc.contributor.authorLavrynenko, R.
dc.date.accessioned2023-05-11T14:04:01Z
dc.date.available2023-05-11T14:04:01Z
dc.date.issued2023
dc.descriptionThe work was performed as part of the state budget research project “Development of methods and algorithms for combined learning of deep neuro-neo-fuzzy systems under short training set conditions” (state registration number 0122U001701) of Artificial Intelligence Department of Kharkiv National University of Radio Electronics.
dc.description.abstractIn this paper a novel approach for semantically robust unpaired image translation is presented. CLIPTraVeLGAN replaces the Siamese network in TraVeLGAN with a contrastively pretrained language-image model (CLIP) with frozen weights. This approach significantly simplifies the model selection and training process of TraVeLGAN, making it more robust and easier to use.
dc.identifier.citationBodyanskiy Y. CLIPTraVeLGAN for Semantically Robust Unpaired Image Translation / Y. Bodyanskiy, N. Ryabova, R. Lavrynenko // Computational Linguistics and Intelligent Systems (COLINS-2023) : Proc. 7th Int. Conf., April 20–21, 2023. – Kharkiv, 2023. – Volume I (Machine Learning Workshop). – pp.1-12.
dc.identifier.otherurn:nbn:de:0074-3387-8
dc.identifier.urihttps://openarchive.nure.ua/handle/document/22867
dc.language.isoen
dc.subjectImage-to-image translation, GAN, CLIP, Transfer knowledge
dc.titleCLIPTraVeLGAN for Semantically Robust Unpaired Image Translation
dc.typeConference proceedings
dspace.entity.typePublication

Файли

Оригінальний пакет
Зараз показано 1 - 1 з 1
Завантаження...
Зображення мініатюри
Назва:
CLIPTraVeLGAN_CEUR_3387.pdf
Розмір:
2.5 MB
Формат:
Adobe Portable Document Format
Ліцензійний пакет
Зараз показано 1 - 1 з 1
Немає доступних мініатюр
Назва:
license.txt
Розмір:
9.64 KB
Формат:
Item-specific license agreed upon to submission
Опис: