no code implementations • 7 Dec 2018 • Idoia Ruiz, Bogdan Raducanu, Rakesh Mehta, Jaume Amores
Additionally, we propose and analyse network distillation as a learning strategy to reduce the computational cost of the deep learning approach at test time.
no code implementations • 14 Jul 2014 • Alejandro González, Sebastian Ramos, David Vázquez, Antonio M. López, Jaume Amores
In particular, we propose to use two-stage classifiers which not only rely on the image descriptors required by the base classifiers but also on the response of such base classifiers in a given spatiotemporal neighborhood.