With no other methodological innovation than a carefully designed training, our ResNet model achieved an AUC = 0.955 (0.953 - 0.956) on a combined test set of 61007 test images from different public datasets, which is in line or even better than what other more complex deep learning models reported in the literature.
We experimentally validate whether using coarse-to-fine models instead of one-stage models is appropriate or not for segmenting the optic disc and the optic cup in color fundus images. We observed that models trained with the right amount of data can perform much better than coarse-to-find approaches.
Cuando aplicamos inteligencia artificial en medicina, solemos seguir uno de dos enfoques: o bien utilizar modelos que ya existen para resolver un problema nuevo, o bien proponer un modelo nuevo para resolver problemas que ya existen. En todos los …
We develop a deep neural network that automatically extracts contextual features from patches in sketches, trained with 3D models rendered with non-photorealistic techniques. Our method is able to find dense correspondences between real world sketches!