Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Jeonghyo Ha"'
Publikováno v:
IEEE Access, Vol 10, Pp 45179-45189 (2022)
Blind super-resolution (blind-SR) is an important task in the field of computer vision and has various applications in real-world. Blur kernel estimation is the main element of blind-SR along with the adaptive SR networks and a more accurately estima
Externí odkaz:
https://doaj.org/article/28f6353a6d5e436c9aec7778a6b9bb35
Publikováno v:
IEEE Access, Vol 8, Pp 137672-137682 (2020)
The development of convolutional neural networks (CNN) has remarkably improved the current research on single image super-resolution (SISR). Several high-quality studies have been performed on reconstruction accuracy and perceptual quality, which are
Externí odkaz:
https://doaj.org/article/a8d25cbb37064eeea9f912cdbd240154
Publikováno v:
Lecture Notes in Mechanical Engineering ISBN: 9789811648021
Inspections for maintenance of electricity facility are performed by patrols which are always in a potentially dangerous traffic accident. In this study, we address the inspection procedure with leveraging advanced deep learning algorithms on images
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::48f92e453fc4344df3bba4307a1a4942
https://doi.org/10.1007/978-981-16-4803-8_38
https://doi.org/10.1007/978-981-16-4803-8_38
Publikováno v:
Proceedings of the 2018 International Conference on Information Science and System.
In this paper, we describe a training methodology of convolutional neural networks(CNNs) using data from a different domain when the number of training data in the test domain is small. Training a CNN for classification without enough data might lead
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::470d11ce509ebd961829668d607f879d
https://doi.org/10.1145/3209914.3209927
https://doi.org/10.1145/3209914.3209927