Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Hanieh Shojaei"'
Reliable deep learning models require not only accurate predictions but also well-calibrated confidence estimates to ensure dependable uncertainty estimation. This is crucial in safety-critical applications like autonomous driving, which depend on ra
Externí odkaz:
http://arxiv.org/abs/2411.11935
Publikováno v:
International Journal of Digital Earth, Vol 15, Iss 1, Pp 148-163 (2022)
This paper introduces an improved convolutional neural network based on the conventional U-Net for simulating built-up land expansion. The proposed method hires a pixel-wise semantic segmentation approach considering the spatial drivers affecting urb
Externí odkaz:
https://doaj.org/article/c5dd9acc56b246bd8cfbeab9b4268694
Autor:
Shojaei, Hanieh1 (AUTHOR) h.shojaee74@gmail.com, Nadi, Saeed1,2 (AUTHOR), Shafizadeh-Moghadam, Hossein3 (AUTHOR), Tayyebi, Amin4 (AUTHOR), Van Genderen, John5 (AUTHOR)
Publikováno v:
International Journal of Digital Earth. Jan2022, Vol. 15 Issue 1, p148-163. 16p.