361 citations · 518 across the 20 of their papers we have counts for
6 papers · 1 filter
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training
Pau de Jorge, Adel Bibi, Riccardo Volpi +4
Recently, Wong et al. showed that adversarial training with single-step FGSM leads to a characteristic failure mode named Catastrophic Overfitting (CO), in which a model becomes su…
Reliable Uncertainties for Bayesian Neural Networks using Alpha-divergences
Hector J. Hortua, Luigi Malago, Riccardo Volpi
Bayesian Neural Networks (BNNs) often result uncalibrated after training, usually tending towards overconfidence. Devising effective calibration methods with low impact in terms of…
Natural Reweighted Wake-Sleep
Csongor Várady, Riccardo Volpi, Luigi Malagò +1
Helmholtz Machines (HMs) are a class of generative models composed of two Sigmoid Belief Networks (SBNs), acting respectively as an encoder and a decoder. These models are commonly…
Natural Alpha Embeddings
Riccardo Volpi, Luigi Malagò
Learning an embedding for a large collection of items is a popular approach to overcome the computational limitations associated to one-hot encodings. The aim of item embedding is…
Addressing Model Vulnerability to Distributional Shifts over Image Transformation Sets
Riccardo Volpi, Vittorio Murino
We are concerned with the vulnerability of computer vision models to distributional shifts. We formulate a combinatorial optimization problem that allows evaluating the regions in…
Learning in Variational Autoencoders with Kullback-Leibler and Renyi Integral Bounds
Septimia Sârbu, Riccardo Volpi, Alexandra Peşte +1
In this paper we propose two novel bounds for the log-likelihood based on Kullback-Leibler and the Rényi divergences, which can be used for variational inference and in particular…