4 papers · 1 filter
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…
-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…
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…
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…