Search Results for author: Pietro Zanuttigh

Found 30 papers, 9 papers with code

NIGHT -- Non-Line-of-Sight Imaging from Indirect Time of Flight Data

1 code implementation28 Mar 2024 Matteo Caligiuri, Adriano Simonetto, Gianluca Agresti, Pietro Zanuttigh

The acquisition of objects outside the Line-of-Sight of cameras is a very intriguing but also extremely challenging research topic.

A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation

no code implementations28 Feb 2024 Francesco Barbato, Umberto Michieli, Mehmet Kerim Yucel, Pietro Zanuttigh, Mete Ozay

To this end, we design a small, modular, and efficient (just 2GFLOPs to process a Full HD image) system to enhance input data for robust downstream multimedia understanding with minimal computational cost.

Data Augmentation Domain Adaptation +2

ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Data

no code implementations2 Feb 2024 Carmen Martin-Turrero, Maxence Bouvier, Manuel Breitenstein, Pietro Zanuttigh, Vincent Parret

We propose a novel hybrid pipeline composed of asynchronous sensing and synchronous processing that combines several ideas: (1) an embedding based on PointNet models -- the ALERT module -- that can continuously integrate new and dismiss old events thanks to a leakage mechanism, (2) a flexible readout of the embedded data that allows to feed any downstream model with always up-to-date features at any sampling rate, (3) exploiting the input sparsity in a patch-based approach inspired by Vision Transformer to optimize the efficiency of the method.

Gesture Recognition

RECALL+: Adversarial Web-based Replay for Continual Learning in Semantic Segmentation

no code implementations19 Sep 2023 Chang Liu, Giulia Rizzoli, Francesco Barbato, Andrea Maracani, Marco Toldo, Umberto Michieli, Yi Niu, Pietro Zanuttigh

Catastrophic forgetting of previous knowledge is a critical issue in continual learning typically handled through various regularization strategies.

Continual Learning Incremental Learning +1

Exploiting Multiple Priors for Neural 3D Indoor Reconstruction

no code implementations13 Sep 2023 Federico Lincetto, Gianluca Agresti, Mattia Rossi, Pietro Zanuttigh

In this work, we propose a novel neural implicit modeling method that leverages multiple regularization strategies to achieve better reconstructions of large indoor environments, while relying only on images.

3D Reconstruction

SynDrone -- Multi-modal UAV Dataset for Urban Scenarios

1 code implementation21 Aug 2023 Giulia Rizzoli, Francesco Barbato, Matteo Caligiuri, Pietro Zanuttigh

The development of computer vision algorithms for Unmanned Aerial Vehicles (UAVs) imagery heavily relies on the availability of annotated high-resolution aerial data.

Semantic Segmentation

Continual Road-Scene Semantic Segmentation via Feature-Aligned Symmetric Multi-Modal Network

no code implementations9 Aug 2023 Francesco Barbato, Elena Camuffo, Simone Milani, Pietro Zanuttigh

In this work, we re-frame the task of multimodal semantic segmentation by enforcing a tightly-coupled feature representation and a symmetric information-sharing scheme, which allows our approach to work even when one of the input modalities is missing.

Autonomous Driving Continual Learning +1

Source-Free Domain Adaptation for RGB-D Semantic Segmentation with Vision Transformers

no code implementations23 May 2023 Giulia Rizzoli, Donald Shenaj, Pietro Zanuttigh

With the increasing availability of depth sensors, multimodal frameworks that combine color information with depth data are gaining interest.

Segmentation Semantic Segmentation +2

Asynchronous Federated Continual Learning

1 code implementation7 Apr 2023 Donald Shenaj, Marco Toldo, Alberto Rigon, Pietro Zanuttigh

We introduce a novel federated learning setting (AFCL) where the continual learning of multiple tasks happens at each client with different orderings and in asynchronous time slots.

Continual Learning Federated Learning

DepthFormer: Multimodal Positional Encodings and Cross-Input Attention for Transformer-Based Segmentation Networks

no code implementations8 Nov 2022 Francesco Barbato, Giulia Rizzoli, Pietro Zanuttigh

Most approaches for semantic segmentation use only information from color cameras to parse the scenes, yet recent advancements show that using depth data allows to further improve performances.

Segmentation Semantic Segmentation

Learning with Style: Continual Semantic Segmentation Across Tasks and Domains

no code implementations13 Oct 2022 Marco Toldo, Umberto Michieli, Pietro Zanuttigh

Then, we address the proposed setup by using style transfer techniques to extend knowledge across domains when learning incremental tasks and a robust distillation framework to effectively recollect task knowledge under incremental domain shift.

Autonomous Driving Class Incremental Learning +5

Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning

1 code implementation5 Oct 2022 Donald Shenaj, Eros Fanì, Marco Toldo, Debora Caldarola, Antonio Tavera, Umberto Michieli, Marco Ciccone, Pietro Zanuttigh, Barbara Caputo

Federated Learning (FL) has recently emerged as a possible way to tackle the domain shift in real-world Semantic Segmentation (SS) without compromising the private nature of the collected data.

Autonomous Driving Federated Learning +2

Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation

no code implementations18 Jan 2022 Donald Shenaj, Francesco Barbato, Umberto Michieli, Pietro Zanuttigh

In this paper we introduce the novel task of coarse-to-fine learning of semantic segmentation architectures in presence of domain shift.

Domain Adaptation Knowledge Distillation +1

Lightweight Deep Learning Architecture for MPI Correction and Transient Reconstruction

no code implementations29 Nov 2021 Adriano Simonetto, Gianluca Agresti, Pietro Zanuttigh, Henrik Schäfer

Indirect Time-of-Flight cameras (iToF) are low-cost devices that provide depth images at an interactive frame rate.

Road Scenes Segmentation Across Different Domains by Disentangling Latent Representations

1 code implementation6 Aug 2021 Francesco Barbato, Umberto Michieli, Marco Toldo, Pietro Zanuttigh

Deep learning models obtain impressive accuracy in road scenes understanding, however they need a large quantity of labeled samples for their training.

Domain Adaptation Semantic Segmentation

Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation

1 code implementation6 Apr 2021 Francesco Barbato, Marco Toldo, Umberto Michieli, Pietro Zanuttigh

Deep convolutional neural networks for semantic segmentation achieve outstanding accuracy, however they also have a couple of major drawbacks: first, they do not generalize well to distributions slightly different from the one of the training data; second, they require a huge amount of labeled data for their optimization.

Autonomous Driving Clustering +3

Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings

1 code implementation25 Nov 2020 Marco Toldo, Umberto Michieli, Pietro Zanuttigh

Deep learning frameworks allowed for a remarkable advancement in semantic segmentation, but the data hungry nature of convolutional networks has rapidly raised the demand for adaptation techniques able to transfer learned knowledge from label-abundant domains to unlabeled ones.

Clustering Semantic Segmentation +1

GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild

no code implementations ECCV 2020 Umberto Michieli, Edoardo Borsato, Luca Rossi, Pietro Zanuttigh

To tackle part-level ambiguity and localization we propose a novel adjacency graph-based module that aims at matching the relative spatial relationships between ground truth and predicted parts.

Graph Matching Object +1

Unsupervised Domain Adaptation in Semantic Segmentation: a Review

no code implementations21 May 2020 Marco Toldo, Andrea Maracani, Umberto Michieli, Pietro Zanuttigh

The aim of this paper is to give an overview of the recent advancements in the Unsupervised Domain Adaptation (UDA) of deep networks for semantic segmentation.

Autonomous Driving Multi-Task Learning +2

Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Training

no code implementations27 Apr 2020 Teo Spadotto, Marco Toldo, Umberto Michieli, Pietro Zanuttigh

We introduce a novel UDA framework where a standard supervised loss on labeled synthetic data is supported by an adversarial module and a self-training strategy aiming at aligning the two domain distributions.

Segmentation Semantic Segmentation +1

Knowledge Distillation for Incremental Learning in Semantic Segmentation

no code implementations8 Nov 2019 Umberto Michieli, Pietro Zanuttigh

Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones.

Image Classification Incremental Learning +5

Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation

no code implementations2 Sep 2019 Umberto Michieli, Matteo Biasetton, Gianluca Agresti, Pietro Zanuttigh

A recently proposed workaround is to train deep networks using synthetic data, but the domain shift between real world and synthetic representations limits the performance.

Autonomous Driving Semantic Segmentation +1

Incremental Learning Techniques for Semantic Segmentation

2 code implementations31 Jul 2019 Umberto Michieli, Pietro Zanuttigh

To tackle this task we propose to distill the knowledge of the previous model to retain the information about previously learned classes, whilst updating the current model to learn the new ones.

Disjoint 10-1 Disjoint 15-1 +14

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