361 citations · 518 across the 20 of their papers we have counts for
25 papers
The CAPSARII Approach to Cyber-Secure Wearable, Ultra-Low-Power Networked Sensors for Soldier Health Monitoring
Luciano Bozzi, Christian Celidonio, Umberto Nuzzi +15
The European Defence Agency's revised Capability Development Plan (CDP) identifies as a priority improving ground combat capabilities by enhancing soldiers' equipment for better pr…
RaSP: Relation-aware Semantic Prior for Weakly Supervised Incremental Segmentation
Subhankar Roy, Riccardo Volpi, Gabriela Csurka +1
Class-incremental semantic image segmentation assumes multiple model updates, each enriching the model to segment new categories. This is typically carried out by providing expensi…
Reliability in Semantic Segmentation: Are We on the Right Track?
Pau de Jorge, Riccardo Volpi, Philip Torr +1
Motivated by the increasing popularity of transformers in computer vision, in recent times there has been a rapid development of novel architectures. While in-domain performance fo…
Semantic Image Segmentation: Two Decades of Research
Gabriela Csurka, Riccardo Volpi, Boris Chidlovskii
Semantic image segmentation (SiS) plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image. T…
On the Road to Online Adaptation for Semantic Image Segmentation
Riccardo Volpi, Pau de Jorge, Diane Larlus +1
We propose a new problem formulation and a corresponding evaluation framework to advance research on unsupervised domain adaptation for semantic image segmentation. The overall goa…
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…
Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey
Gabriela Csurka, Riccardo Volpi, Boris Chidlovskii
Semantic segmentation plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image. Yet, the stat…
Automatic Feature Extraction for Heartbeat Anomaly Detection
Robert-George Colt, Csongor-Huba Várady, Riccardo Volpi +1
We focus on automatic feature extraction for raw audio heartbeat sounds, aimed at anomaly detection applications in healthcare. We learn features with the help of an autoencoder co…
Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning
Riccardo Volpi, Diane Larlus, Grégory Rogez
Most standard learning approaches lead to fragile models which are prone to drift when sequentially trained on samples of a different nature - the well-known "catastrophic forgetti…
Accelerating MCMC algorithms through Bayesian Deep Networks
Hector J. Hortua, Riccardo Volpi, Dimitri Marinelli +1
Markov Chain Monte Carlo (MCMC) algorithms are commonly used for their versatility in sampling from complicated probability distributions. However, as the dimension of the distribu…
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…
Constraining the Reionization History using Bayesian Normalizing Flows
Héctor J. Hortúa, Luigi Malago, Riccardo Volpi
The next generation 21 cm surveys open a new window onto the early stages of cosmic structure formation and provide new insights about the Epoch of Reionization (EoR). However, the…
Parameters Estimation from the 21 cm signal using Variational Inference
Héctor J. Hortúa, Riccardo Volpi, Luigi Malagò
Upcoming experiments such as Hydrogen Epoch of Reionization Array (HERA) and Square Kilometre Array (SKA) are intended to measure the 21cm signal over a wide range of redshifts, re…
Explainable Deep Classification Models for Domain Generalization
Andrea Zunino, Sarah Adel Bargal, Riccardo Volpi +5
Conventionally, AI models are thought to trade off explainability for lower accuracy. We develop a training strategy that not only leads to a more explainable AI system for object…
Learning Unbiased Representations via Mutual Information Backpropagation
Ruggero Ragonesi, Riccardo Volpi, Jacopo Cavazza +1
We are interested in learning data-driven representations that can generalize well, even when trained on inherently biased data. In particular, we face the case where some attribut…
Generative Pseudo-label Refinement for Unsupervised Domain Adaptation
Pietro Morerio, Riccardo Volpi, Ruggero Ragonesi +1
We investigate and characterize the inherent resilience of conditional Generative Adversarial Networks (cGANs) against noise in their conditioning labels, and exploit this fact in…
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…
Parameters Estimation for the Cosmic Microwave Background with Bayesian Neural Networks
Hector J. Hortua, Riccardo Volpi, Dimitri Marinelli +1
In this paper, we present the first study that compares different models of Bayesian Neural Networks (BNNs) to predict the posterior distribution of the cosmological parameters dir…
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…
Generalizing to Unseen Domains via Adversarial Data Augmentation
Riccardo Volpi, Hongseok Namkoong, Ozan Sener +3
We are concerned with learning models that generalize well to different \emph{unseen} domains. We consider a worst-case formulation over data distributions that are near the source…
Adversarial Feature Augmentation for Unsupervised Domain Adaptation
Riccardo Volpi, Pietro Morerio, Silvio Savarese +1
Recent works showed that Generative Adversarial Networks (GANs) can be successfully applied in unsupervised domain adaptation, where, given a labeled source dataset and an unlabele…
Curriculum Dropout
Pietro Morerio, Jacopo Cavazza, Riccardo Volpi +2
Dropout is a very effective way of regularizing neural networks. Stochastically "dropping out" units with a certain probability discourages over-specific co-adaptations of feature…