Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Efimova, Valeria"'
Nowadays, there are many diffusion and autoregressive models that show impressive results for generating images from text and other input domains. However, these methods are not intended for ultra-high-resolution image synthesis. Vector graphics are
Externí odkaz:
http://arxiv.org/abs/2306.06441
Neural style transfer draws researchers' attention, but the interest focuses on bitmap images. Various models have been developed for bitmap image generation both online and offline with arbitrary and pre-trained styles. However, the style transfer b
Externí odkaz:
http://arxiv.org/abs/2303.03405
Generative Adversarial Networks (GAN) have motivated a rapid growth of the domain of computer image synthesis. As almost all the existing image synthesis algorithms consider an image as a pixel matrix, the high-resolution image synthesis is complicat
Externí odkaz:
http://arxiv.org/abs/2205.07301
Predicting dataset size for neural network fine-tuning with a given quality in object detection task
Publikováno v:
In Procedia Computer Science 2023 229:158-167
Publikováno v:
In Procedia Computer Science 2023 229:47-54
Publikováno v:
In Procedia Computer Science 2022 212:378-386
Many algorithms for data analysis exist, especially for classification problems. To solve a data analysis problem, a proper algorithm should be chosen, and also its hyperparameters should be selected. In this paper, we present a new method for the si
Externí odkaz:
http://arxiv.org/abs/1611.02053
Autor:
Efimova, Valeria S.
Publikováno v:
PALAEOBULGARICA / СТАРОБЪЛГАРИСТИКА / PALAEOBULGARICA. (1):151-156
Externí odkaz:
https://www.ceeol.com/search/article-detail?id=938174
Autor:
Efimova, Valeria S.
Publikováno v:
PALAEOBULGARICA / СТАРОБЪЛГАРИСТИКА / PALAEOBULGARICA. (4):108-115
Externí odkaz:
https://www.ceeol.com/search/article-detail?id=814865
Publikováno v:
In Procedia Computer Science 2018 136:144-153