1 code implementation • ICLR 2022 • Chen Jin, Ryutaro Tanno, Thomy Mertzanidou, Eleftheria Panagiotaki, Daniel C. Alexander
Many computer vision systems require low-cost segmentation algorithms based on deep learning, either because of the enormous size of input images or limited computational budget.
1 code implementation • 29 Jul 2020 • Chen Jin, Ryutaro Tanno, Mou-Cheng Xu, Thomy Mertzanidou, Daniel C. Alexander
We demonstrate on three publicly available high-resolution image datasets that the foveation module consistently improves segmentation performance over the cases trained with patches of fixed FoV/resolution trade-off.