no code implementations • 6 Aug 2019 • Bojana Gajic, Ariel Amato, Ramon Baldrich, Carlo Gatta
Training a Siamese architecture for re-identification with a large number of identities is a challenging task due to the difficulty of finding relevant negative samples efficiently.
no code implementations • 25 Nov 2015 • Adriana Romero, Carlo Gatta, Gustau Camps-Valls
This paper introduces the use of single layer and deep convolutional networks for remote sensing data analysis.
3 code implementations • 19 Dec 2014 • Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, Yoshua Bengio
In this paper, we extend this idea to allow the training of a student that is deeper and thinner than the teacher, using not only the outputs but also the intermediate representations learned by the teacher as hints to improve the training process and final performance of the student.
no code implementations • 24 Feb 2014 • Adriana Romero, Petia Radeva, Carlo Gatta
We propose a meta-parameter free, off-the-shelf, simple and fast unsupervised feature learning algorithm, which exploits a new way of optimizing for sparsity.
Ranked #104 on Image Classification on STL-10