Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Mete Can Kaya"'
Autor:
G.B. Akar, Mete Can Kaya, Basar Kutukcu, Faruk Ugurcali, Kadircan Becek, Savas Ozkan, Alperen Inci
Publikováno v:
SIU
In this paper, we present a binarized neural network structure for inverse problems. In this structure, memory requirements and computation time are significantly reduced with a negligible performance drop compared to full-precision models. For this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8b84bcdd60c3d0f031cf3e13cdbc933c
https://doi.org/10.1109/siu49456.2020.9302129
https://doi.org/10.1109/siu49456.2020.9302129
Autor:
Gozde Bozdagi Akar, Mete Can Kaya
Publikováno v:
SIU
In this paper, we present a Unet architecture made of octave convolution for dental image segmentation problem. In this architecture, the requirements for memory and accuracy are significantly improved compared to previous works in the literature. Co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3c404803ba8cf4a3b7c8ab52752de4a8
https://doi.org/10.1109/siu49456.2020.9302495
https://doi.org/10.1109/siu49456.2020.9302495