no code implementations • 10 Dec 2023 • Hakim Bouchal, Ahror Belaid
Segmentation of Arabic manuscripts into lines of text and words is an important step to make recognition systems more efficient and accurate.
1 code implementation • 29 Jul 2023 • Hicham Messaoudi, Ahror Belaid, Douraied Ben Salem, Pierre-Henri Conze
In this paper, we introduce an efficient way to transfer the efficiency of a 2D classification network trained on natural images to 2D, 3D uni- and multi-modal medical image segmentation applications.
no code implementations • 22 Nov 2020 • Hicham Messaoudi, Ahror Belaid, Mohamed Lamine Allaoui, Ahcene Zetout, Mohand Said Allili, Souhil Tliba, Douraied Ben Salem, Pierre-Henri Conze
As the input data is in 3D, the first layers of the encoder are devoted to the reduction of the third dimension in order to fit the input of the EfficientNet network.