Bodyanskiy, Y.Ryabova, N.Lavrynenko, R.2023-05-112023-05-112023Bodyanskiy 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.urn:nbn:de:0074-3387-8https://openarchive.nure.ua/handle/document/22867The 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.In 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.enImage-to-image translation, GAN, CLIP, Transfer knowledgeConference proceedings