no code implementations • 14 Apr 2020 • Mo Deng, Shuai Li, Iksung Kang, Nicholas X. Fang, George Barbastathis
That is, the higher the entropy of the training images, the weaker the regularization effect can be imposed.
no code implementations • 26 Jul 2019 • Mo Deng, Shuai Li, Alexandre Goy, Iksung Kang, George Barbastathis
The quality of inverse problem solutions obtained through deep learning [Barbastathis et al, 2019] is limited by the nature of the priors learned from examples presented during the training phase.
no code implementations • 19 Nov 2018 • Mo Deng, Shuai Li, George Barbastathis
Deep Neural Network (DNN)-based image reconstruction, despite many successes, often exhibits uneven fidelity between high and low spatial frequency bands.