Search Results for author: Davide Maltoni

Found 30 papers, 12 papers with code

ONOT: a High-Quality ICAO-compliant Synthetic Mugshot Dataset

no code implementations17 Apr 2024 Nicolò Di Domenico, Guido Borghi, Annalisa Franco, Davide Maltoni

Following this intuition, in this paper we introduce ONOT, a synthetic dataset specifically focused on the generation of high-quality faces in adherence to the requirements of the ISO/IEC 39794-5 standards that, following the guidelines of the International Civil Aviation Organization (ICAO), defines the interchange formats of face images in electronic Machine-Readable Travel Documents (eMRTD).

Dealing with Subject Similarity in Differential Morphing Attack Detection

3 code implementations11 Apr 2024 Nicolò Di Domenico, Guido Borghi, Annalisa Franco, Davide Maltoni

The advent of morphing attacks has posed significant security concerns for automated Face Recognition systems, raising the pressing need for robust and effective Morphing Attack Detection (MAD) methods able to effectively address this issue.

Face Recognition

V-MAD: Video-based Morphing Attack Detection in Operational Scenarios

no code implementations10 Apr 2024 Guido Borghi, Annalisa Franco, Nicolò Di Domenico, Matteo Ferrara, Davide Maltoni

In response to the rising threat of the face morphing attack, this paper introduces and explores the potential of Video-based Morphing Attack Detection (V-MAD) systems in real-world operational scenarios.

Face Verification

Continual Learning by Three-Phase Consolidation

no code implementations12 Mar 2024 Davide Maltoni, Lorenzo Pellegrini

TPC (Three-Phase Consolidation) is here introduced as a simple but effective approach to continually learn new classes (and/or instances of known classes) while controlling forgetting of previous knowledge.

Continual Learning

Enabling On-device Continual Learning with Binary Neural Networks

no code implementations18 Jan 2024 Lorenzo Vorabbi, Davide Maltoni, Guido Borghi, Stefano Santi

On-device learning remains a formidable challenge, especially when dealing with resource-constrained devices that have limited computational capabilities.

Continual Learning Quantization

On-Device Learning with Binary Neural Networks

no code implementations29 Aug 2023 Lorenzo Vorabbi, Davide Maltoni, Stefano Santi

Existing Continual Learning (CL) solutions only partially address the constraints on power, memory and computation of the deep learning models when deployed on low-power embedded CPUs.

Continual Learning Quantization

Arithmetic with Language Models: from Memorization to Computation

no code implementations2 Aug 2023 Davide Maltoni, Matteo Ferrara

A better understanding of the emergent computation and problem-solving capabilities of recent large language models is of paramount importance to further improve them and broaden their applicability.

Language Modelling Memorization

Detecting Morphing Attacks via Continual Incremental Training

no code implementations27 Jul 2023 Lorenzo Pellegrini, Guido Borghi, Annalisa Franco, Davide Maltoni

Scenarios in which restrictions in data transfer and storage limit the possibility to compose a single dataset -- also exploiting different data sources -- to perform a batch-based training procedure, make the development of robust models particularly challenging.

Continual Learning

Input Layer Binarization with Bit-Plane Encoding

no code implementations4 May 2023 Lorenzo Vorabbi, Davide Maltoni, Stefano Santi

Binary Neural Networks (BNNs) use 1-bit weights and activations to efficiently execute deep convolutional neural networks on edge devices.


Region Prediction for Efficient Robot Localization on Large Maps

1 code implementation1 Mar 2023 Matteo Scucchia, Davide Maltoni

In topological SLAM the recognition takes place by comparing a signature (or feature vector) associated to the current node with the signatures of the nodes in the known map.

Loop Closure Detection Simultaneous Localization and Mapping

On the challenges to learn from Natural Data Streams

no code implementations9 Jan 2023 Guido Borghi, Gabriele Graffieti, Davide Maltoni

In real-world contexts, sometimes data are available in form of Natural Data Streams, i. e. data characterized by a streaming nature, unbalanced distribution, data drift over a long time frame and strong correlation of samples in short time ranges.

Incremental Learning

Architect, Regularize and Replay (ARR): a Flexible Hybrid Approach for Continual Learning

no code implementations6 Jan 2023 Vincenzo Lomonaco, Lorenzo Pellegrini, Gabriele Graffieti, Davide Maltoni

In recent years we have witnessed a renewed interest in machine learning methodologies, especially for deep representation learning, that could overcome basic i. i. d.

Class Incremental Learning Incremental Learning +1

Morphing Attack Potential

1 code implementation28 Apr 2022 Matteo Ferrara, Annalisa Franco, Davide Maltoni, Christoph Busch

In security systems the risk assessment in the sense of common criteria testing is a very relevant topic; this requires quantifying the attack potential in terms of the expertise of the attacker, his knowledge about the target and access to equipment.

Face Recognition

Generative Negative Replay for Continual Learning

no code implementations12 Apr 2022 Gabriele Graffieti, Davide Maltoni, Lorenzo Pellegrini, Vincenzo Lomonaco

Learning continually is a key aspect of intelligence and a necessary ability to solve many real-life problems.

Continual Learning

CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions

1 code implementation14 Sep 2020 Vincenzo Lomonaco, Lorenzo Pellegrini, Pau Rodriguez, Massimo Caccia, Qi She, Yu Chen, Quentin Jodelet, Ruiping Wang, Zheda Mai, David Vazquez, German I. Parisi, Nikhil Churamani, Marc Pickett, Issam Laradji, Davide Maltoni

In the last few years, we have witnessed a renewed and fast-growing interest in continual learning with deep neural networks with the shared objective of making current AI systems more adaptive, efficient and autonomous.

Benchmarking Continual Learning

Latent Replay for Real-Time Continual Learning

3 code implementations2 Dec 2019 Lorenzo Pellegrini, Gabriele Graffieti, Vincenzo Lomonaco, Davide Maltoni

Continual learning techniques, where complex models are incrementally trained on small batches of new data, can make the learning problem tractable even for CPU-only embedded devices enabling remarkable levels of adaptiveness and autonomy.

Continual Learning valid

Rehearsal-Free Continual Learning over Small Non-I.I.D. Batches

5 code implementations8 Jul 2019 Vincenzo Lomonaco, Davide Maltoni, Lorenzo Pellegrini

Ideally, continual learning should be triggered by the availability of short videos of single objects and performed on-line on on-board hardware with fine-grained updates.

Class Incremental Learning Object Recognition

Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challenges

no code implementations29 Jun 2019 Timothée Lesort, Vincenzo Lomonaco, Andrei Stoian, Davide Maltoni, David Filliat, Natalia Díaz-Rodríguez

An important challenge for machine learning is not necessarily finding solutions that work in the real world but rather finding stable algorithms that can learn in real world.

BIG-bench Machine Learning Continual Learning

Continual Reinforcement Learning in 3D Non-stationary Environments

1 code implementation24 May 2019 Vincenzo Lomonaco, Karan Desai, Eugenio Culurciello, Davide Maltoni

High-dimensional always-changing environments constitute a hard challenge for current reinforcement learning techniques.

reinforcement-learning Reinforcement Learning (RL)

Face morphing detection in the presence of printing/scanning and heterogeneous image sources

no code implementations25 Jan 2019 Matteo Ferrara, Annalisa Franco, Davide Maltoni

Face morphing represents nowadays a big security threat in the context of electronic identity documents as well as an interesting challenge for researchers in the field of face recognition.

Data Augmentation Face Recognition

Don't forget, there is more than forgetting: new metrics for Continual Learning

no code implementations31 Oct 2018 Natalia Díaz-Rodríguez, Vincenzo Lomonaco, David Filliat, Davide Maltoni

Continual learning consists of algorithms that learn from a stream of data/tasks continuously and adaptively thought time, enabling the incremental development of ever more complex knowledge and skills.

Attribute Computational Efficiency +2

Continuous Learning in Single-Incremental-Task Scenarios

1 code implementation22 Jun 2018 Davide Maltoni, Vincenzo Lomonaco

It was recently shown that architectural, regularization and rehearsal strategies can be used to train deep models sequentially on a number of disjoint tasks without forgetting previously acquired knowledge.

Class Incremental Learning Incremental Learning

CORe50: a New Dataset and Benchmark for Continuous Object Recognition

1 code implementation9 May 2017 Vincenzo Lomonaco, Davide Maltoni

Continuous/Lifelong learning of high-dimensional data streams is a challenging research problem.

Continuous Object Recognition Object

Semi-supervised Tuning from Temporal Coherence

1 code implementation10 Nov 2015 Davide Maltoni, Vincenzo Lomonaco

Recent works demonstrated the usefulness of temporal coherence to regularize supervised training or to learn invariant features with deep architectures.

General Classification

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