Search Results for author: Marco Ciccone

Found 18 papers, 7 papers with code

A Marriage between Adversarial Team Games and 2-player Games: Enabling Abstractions, No-regret Learning, and Subgame Solving

no code implementations18 Jun 2022 Luca Carminati, Federico Cacciamani, Marco Ciccone, Nicola Gatti

This work shows that we can recover from this weakness by bridging the gap between sequential adversarial team games and 2-player games.

Fault-Aware Design and Training to Enhance DNNs Reliability with Zero-Overhead

no code implementations28 May 2022 Niccolò Cavagnero, Fernando Dos Santos, Marco Ciccone, Giuseppe Averta, Tatiana Tommasi, Paolo Rech

Deep Neural Networks (DNNs) enable a wide series of technological advancements, ranging from clinical imaging, to predictive industrial maintenance and autonomous driving.

Autonomous Driving

Improving Generalization in Federated Learning by Seeking Flat Minima

1 code implementation22 Mar 2022 Debora Caldarola, Barbara Caputo, Marco Ciccone

Models trained in federated settings often suffer from degraded performances and fail at generalizing, especially when facing heterogeneous scenarios.

Domain Generalization Federated Learning +2

FedDrive: Generalizing Federated Learning to Semantic Segmentation in Autonomous Driving

1 code implementation28 Feb 2022 Lidia Fantauzzo, Eros Fani', Debora Caldarola, Antonio Tavera, Fabio Cermelli, Marco Ciccone, Barbara Caputo

For similar reasons, Federated Learning has been recently introduced as a new machine learning paradigm aiming to learn a global model while preserving privacy and leveraging data on millions of remote devices.

Autonomous Driving Domain Generalization +3

Speeding up Heterogeneous Federated Learning with Sequentially Trained Superclients

1 code implementation26 Jan 2022 Riccardo Zaccone, Andrea Rizzardi, Debora Caldarola, Marco Ciccone, Barbara Caputo

data severely impairs both the performance of the trained neural network and its convergence rate, increasing the number of communication rounds requested to reach a performance comparable to that of the centralized scenario.

Federated Learning Image Classification

Public Information Representation for Adversarial Team Games

no code implementations25 Jan 2022 Luca Carminati, Federico Cacciamani, Marco Ciccone, Nicola Gatti

Interestingly, we show that our game is more expressive than the original extensive-form game as any state/action abstraction of the extensive-form game can be captured by our representation, while the reverse does not hold.

Incremental Learning in Semantic Segmentation from Image Labels

1 code implementation CVPR 2022 Fabio Cermelli, Dario Fontanel, Antonio Tavera, Marco Ciccone, Barbara Caputo

As opposed to existing approaches, that need to generate pseudo-labels offline, we use an auxiliary classifier, trained with image-level labels and regularized by the segmentation model, to obtain pseudo-supervision online and update the model incrementally.

Incremental Learning Semantic Segmentation

Cluster-driven Graph Federated Learning over Multiple Domains

no code implementations29 Apr 2021 Debora Caldarola, Massimiliano Mancini, Fabio Galasso, Marco Ciccone, Emanuele Rodolà, Barbara Caputo

Clustering may reduce heterogeneity by identifying the domains, but it deprives each cluster model of the data and supervision of others.

Federated Learning

Multi-Agent Coordination in Adversarial Environments through Signal Mediated Strategies

no code implementations9 Feb 2021 Federico Cacciamani, Andrea Celli, Marco Ciccone, Nicola Gatti

Team members can coordinate their strategies before the beginning of the game, but are unable to communicate during the playing phase of the game.

A Differentiable Recurrent Surface for Asynchronous Event-Based Data

1 code implementation ECCV 2020 Marco Cannici, Marco Ciccone, Andrea Romanoni, Matteo Matteucci

Dynamic Vision Sensors (DVSs) asynchronously stream events in correspondence of pixels subject to brightness changes.

Optical Flow Estimation

Coordination in Adversarial Sequential Team Games via Multi-Agent Deep Reinforcement Learning

no code implementations16 Dec 2019 Andrea Celli, Marco Ciccone, Raffaele Bongo, Nicola Gatti

Many real-world applications involve teams of agents that have to coordinate their actions to reach a common goal against potential adversaries.

reinforcement-learning

Attention Mechanisms for Object Recognition with Event-Based Cameras

no code implementations25 Jul 2018 Marco Cannici, Marco Ciccone, Andrea Romanoni, Matteo Matteucci

Event-based cameras are neuromorphic sensors capable of efficiently encoding visual information in the form of sparse sequences of events.

Event-based vision Object Recognition +1

ReConvNet: Video Object Segmentation with Spatio-Temporal Features Modulation

no code implementations14 Jun 2018 Francesco Lattari, Marco Ciccone, Matteo Matteucci, Jonathan Masci, Francesco Visin

We introduce ReConvNet, a recurrent convolutional architecture for semi-supervised video object segmentation that is able to fast adapt its features to focus on any specific object of interest at inference time.

Semantic Segmentation Semi-Supervised Video Object Segmentation +1

Asynchronous Convolutional Networks for Object Detection in Neuromorphic Cameras

no code implementations21 May 2018 Marco Cannici, Marco Ciccone, Andrea Romanoni, Matteo Matteucci

Event-based cameras, also known as neuromorphic cameras, are bioinspired sensors able to perceive changes in the scene at high frequency with low power consumption.

object-detection Object Detection

NAIS-Net: Stable Deep Networks from Non-Autonomous Differential Equations

1 code implementation NeurIPS 2018 Marco Ciccone, Marco Gallieri, Jonathan Masci, Christian Osendorfer, Faustino Gomez

This paper introduces Non-Autonomous Input-Output Stable Network(NAIS-Net), a very deep architecture where each stacked processing block is derived from a time-invariant non-autonomous dynamical system.

Multi-View Stereo with Single-View Semantic Mesh Refinement

no code implementations16 Aug 2017 Andrea Romanoni, Marco Ciccone, Francesco Visin, Matteo Matteucci

In this paper we propose a novel method to refine both the geometry and the semantic labeling of a given mesh.

3D Reconstruction

Cannot find the paper you are looking for? You can Submit a new open access paper.