collaborators

5 papers

cs.LG2020

IntroVAC: Introspective Variational Classifiers for Learning Interpretable Latent Subspaces

Marco Maggipinto, Matteo Terzi, Gian Antonio Susto

Learning useful representations of complex data has been the subject of extensive research for many years. With the diffusion of Deep Neural Networks, Variational Autoencoders have…

cs.LG2020

-Variational Classifiers Under Attack

Marco Maggipinto, Matteo Terzi, Gian Antonio Susto

Deep Neural networks have gained lots of attention in recent years thanks to the breakthroughs obtained in the field of Computer Vision. However, despite their popularity, it has b…

cs.LG2020

Adversarial Training Reduces Information and Improves Transferability

Matteo Terzi, Alessandro Achille, Marco Maggipinto +1

Recent results show that features of adversarially trained networks for classification, in addition to being robust, enable desirable properties such as invertibility. The latter p…

cs.LG2019

Directional Adversarial Training for Cost Sensitive Deep Learning Classification Applications

Matteo Terzi, Gian Antonio Susto, Pratik Chaudhari

In many real-world applications of Machine Learning it is of paramount importance not only to provide accurate predictions, but also to ensure certain levels of robustness. Adversa…

cs.RO2019

Robot kinematic structure classification from time series of visual data

Alberto Dalla Libera, Matteo Terzi, Alessandro Rossi +2

In this paper we present a novel algorithm to solve the robot kinematic structure identification problem. Given a time series of data, typically obtained processing a set of visual…