2 code implementations • 27 Jan 2018 • Marco Carletti, Marco Godi, Maedeh Aghaei, Francesco Giuliari, Marco Cristani
In deep learning, visualization techniques extract the salient patterns exploited by deep networks for image classification, focusing on single images; no effort has been spent in investigating whether these patterns are systematically related to precise semantic entities over multiple images belonging to a same class, thus failing to capture the very understanding of the image class the network has realized.