Fabio Valerio Massoli
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Fabio Valerio Massoli has a total of 223 co-authors. Here are the top co-authors by number of shared publications:
- Alexander Kish
Fermi National Accelerator Laboratory
9 shared publications - Alfredo Davide Ferella
INFN-Laboratori Nazionali del Gran Sasso and Gran Sasso Science Institute, 67100 L’Aquila, Italy
9 shared publications - José A. Matias Lopes
LIBPhys, Department of Physics, University of Coimbra, 3004-516 Coimbra, Portugal
9 shared publications - João M. R. Cardoso
LIBPhys, Department of Physics, University of Coimbra, 3004-516 Coimbra, Portugal
9 shared publications - Laura Baudis
Physik-Institut, University of Zurich, 8057 Zürich, Switzerland
9 shared publications - Manfred Lindner
Max-Planck-Institut für Kernphysik, 69117 Heidelberg, Germany
9 shared publications
Latest Publications
- Open Access
- 3 December 2022
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 55 (5) , 1-37
A Leap among Quantum Computing and Quantum Neural Networks: A Survey
In recent years, Quantum Computing witnessed massive improvements in terms of available resources and algorithms development. The ability to harness quantum phenomena to solve computational problems is a long-standing dream that has drawn the scientific community’s interest since the late ’80s. In such a context, we propose our contribution. First, we introduce basic concepts related to quantum computations, and then we explain the core functionalities of technologies that implement the Gate Model and Adiabatic Quantum Computing paradigms. Finally, we gather, compare, and analyze the current state-of-the-art concerning Quantum Perceptrons and Quantum Neural Networks implementations.
- 3 December 2022
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 55 (5) , 1-37
Open AccessA Leap among Quantum Computing and Quantum Neural Networks: A Survey
In recent years, Quantum Computing witnessed massive improvements in terms of available resources and algorithms development. The ability to harness quantum phenomena to solve computational problems is a long-standing dream that has drawn the scientific community’s interest since the late ’80s. In such a context, we propose our contribution. First, we introduce basic concepts related to quantum computations, and then we explain the core functionalities of technologies that implement the Gate Model and Adiabatic Quantum Computing paradigms. Finally, we gather, compare, and analyze the current state-of-the-art concerning Quantum Perceptrons and Quantum Neural Networks implementations.
- Open Access
A Leap among Quantum Computing and Quantum Neural Networks: A Survey
In recent years, Quantum Computing witnessed massive improvements in terms of available resources and algorithms development. The ability to harness quantum phenomena to solve computational problems is a long-standing dream that has drawn the scientific community's interest since the late 80s. In such a context, we propose our contribution. First, we introduce basic concepts related to quantum computations, and then we explain the core functionalities of technologies that implement the Gate Model and Adiabatic Quantum Computing paradigms. Finally, we gather, compare and analyze the current state-of-the-art concerning Quantum Perceptrons and Quantum Neural Networks implementations.
Open AccessA Leap among Quantum Computing and Quantum Neural Networks: A Survey
In recent years, Quantum Computing witnessed massive improvements in terms of available resources and algorithms development. The ability to harness quantum phenomena to solve computational problems is a long-standing dream that has drawn the scientific community's interest since the late 80s. In such a context, we propose our contribution. First, we introduce basic concepts related to quantum computations, and then we explain the core functionalities of technologies that implement the Gate Model and Adiabatic Quantum Computing paradigms. Finally, we gather, compare and analyze the current state-of-the-art concerning Quantum Perceptrons and Quantum Neural Networks implementations.
- 7 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 33 (6) , 2313-2323
MOCCA: Multilayer One-Class Classification for Anomaly Detection
Anomalies are ubiquitous in all scientific fields and can express an unexpected event due to incomplete knowledge about the data distribution or an unknown process that suddenly comes into play and distorts the observations. Usually, due to such events’ rarity, to train deep learning (DL) models on the anomaly detection (AD) task, scientists only rely on “normal” data, i.e., nonanomalous samples. Thus, letting the neural network infer the distribution beneath the input data. In such a context, we propose a novel framework, named multilayer one-class classification (MOCCA), to train and test DL models on the AD task. Specifically, we applied our approach to autoencoders. A key novelty in our work stems from the explicit optimization of the intermediate representations for the task at hand. Indeed, differently from commonly used approaches that consider a neural network as a single computational block, i.e., using the output of the last layer only, MOCCA explicitly leverages the multilayer structure of deep architectures. Each layer’s feature space is optimized for AD during training, while in the test phase, the deep representations extracted from the trained layers are combined to detect anomalies. With MOCCA, we split the training process into two steps. First, the autoencoder is trained on the reconstruction task only. Then, we only retain the encoder tasked with minimizing the $L_{2}$ distance between the output representation and a reference point, the anomaly-free training data centroid, at each considered layer. Subsequently, we combine the deep features extracted at the various trained layers of the encoder model to detect anomalies at inference time. To assess the performance of the models trained with MOCCA, we conduct extensive experiments on publicly available datasets, namely CIFAR10, MVTec AD, and ShanghaiTech. We show that our proposed method reaches comparable or superior performance to state-of-the-art approaches available in the literature. Finally, we provide a model analysis to give insights regarding the benefits of our training procedure.
- 7 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 33 (6) , 2313-2323
MOCCA: Multilayer One-Class Classification for Anomaly Detection
Anomalies are ubiquitous in all scientific fields and can express an unexpected event due to incomplete knowledge about the data distribution or an unknown process that suddenly comes into play and distorts the observations. Usually, due to such events’ rarity, to train deep learning (DL) models on the anomaly detection (AD) task, scientists only rely on “normal” data, i.e., nonanomalous samples. Thus, letting the neural network infer the distribution beneath the input data. In such a context, we propose a novel framework, named multilayer one-class classification (MOCCA), to train and test DL models on the AD task. Specifically, we applied our approach to autoencoders. A key novelty in our work stems from the explicit optimization of the intermediate representations for the task at hand. Indeed, differently from commonly used approaches that consider a neural network as a single computational block, i.e., using the output of the last layer only, MOCCA explicitly leverages the multilayer structure of deep architectures. Each layer’s feature space is optimized for AD during training, while in the test phase, the deep representations extracted from the trained layers are combined to detect anomalies. With MOCCA, we split the training process into two steps. First, the autoencoder is trained on the reconstruction task only. Then, we only retain the encoder tasked with minimizing the $L_{2}$ distance between the output representation and a reference point, the anomaly-free training data centroid, at each considered layer. Subsequently, we combine the deep features extracted at the various trained layers of the encoder model to detect anomalies at inference time. To assess the performance of the models trained with MOCCA, we conduct extensive experiments on publicly available datasets, namely CIFAR10, MVTec AD, and ShanghaiTech. We show that our proposed method reaches comparable or superior performance to state-of-the-art approaches available in the literature. Finally, we provide a model analysis to give insights regarding the benefits of our training procedure.
- Open Access
MOCCA: Multi-Layer One-Class ClassificAtion for Anomaly Detection
Anomalies are ubiquitous in all scientific fields and can express an unexpected event due to incomplete knowledge about the data distribution or an unknown process that suddenly comes into play and distorts observations. Due to such events' rarity, to train deep learning models on the Anomaly Detection (AD) task, scientists only rely on "normal" data, i.e., non-anomalous samples. Thus, letting the neural network infer the distribution beneath the input data. In such a context, we propose a novel framework, named Multi-layer One-Class ClassificAtion (MOCCA),to train and test deep learning models on the AD task. Specifically, we applied it to autoencoders. A key novelty in our work stems from the explicit optimization of intermediate representations for the AD task. Indeed, differently from commonly used approaches that consider a neural network as a single computational block, i.e., using the output of the last layer only, MOCCA explicitly leverages the multi-layer structure of deep architectures. Each layer's feature space is optimized for AD during training, while in the test phase, the deep representations extracted from the trained layers are combined to detect anomalies. With MOCCA, we split the training process into two steps. First, the autoencoder is trained on the reconstruction task only. Then, we only retain the encoder tasked with minimizing the L_2 distance between the output representation and a reference point, the anomaly-free training data centroid, at each considered layer. Subsequently, we combine the deep features extracted at the various trained layers of the encoder model to detect anomalies at inference time. To assess the performance of the models trained with MOCCA, we conduct extensive experiments on publicly available datasets. We show that our proposed method reaches comparable or superior performance to state-of-the-art approaches available in the literature.
Open AccessMOCCA: Multi-Layer One-Class ClassificAtion for Anomaly Detection
Anomalies are ubiquitous in all scientific fields and can express an unexpected event due to incomplete knowledge about the data distribution or an unknown process that suddenly comes into play and distorts observations. Due to such events' rarity, to train deep learning models on the Anomaly Detection (AD) task, scientists only rely on "normal" data, i.e., non-anomalous samples. Thus, letting the neural network infer the distribution beneath the input data. In such a context, we propose a novel framework, named Multi-layer One-Class ClassificAtion (MOCCA),to train and test deep learning models on the AD task. Specifically, we applied it to autoencoders. A key novelty in our work stems from the explicit optimization of intermediate representations for the AD task. Indeed, differently from commonly used approaches that consider a neural network as a single computational block, i.e., using the output of the last layer only, MOCCA explicitly leverages the multi-layer structure of deep architectures. Each layer's feature space is optimized for AD during training, while in the test phase, the deep representations extracted from the trained layers are combined to detect anomalies. With MOCCA, we split the training process into two steps. First, the autoencoder is trained on the reconstruction task only. Then, we only retain the encoder tasked with minimizing the L_2 distance between the output representation and a reference point, the anomaly-free training data centroid, at each considered layer. Subsequently, we combine the deep features extracted at the various trained layers of the encoder model to detect anomalies at inference time. To assess the performance of the models trained with MOCCA, we conduct extensive experiments on publicly available datasets. We show that our proposed method reaches comparable or superior performance to state-of-the-art approaches available in the literature.
- 1 July 2021
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 93
Psycho-acoustics inspired automatic speech recognition
- 1 July 2021
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 93
Psycho-acoustics inspired automatic speech recognition
- 1 December 2020
- Published by Elsevier in Pattern Recognition Letters
- Vol. 140, 222-229
Cross-resolution face recognition adversarial attacks
- 1 December 2020
- Published by Elsevier in Pattern Recognition Letters
- Vol. 140, 222-229
Cross-resolution face recognition adversarial attacks
- 14 October 2020
- Published by Springer Nature
- p. 352-360
Cross-Resolution Deep Features Based Image Search
- 14 October 2020
- Published by Springer Nature
- p. 352-360
Cross-Resolution Deep Features Based Image Search
- Open Access
Cross-Resolution Learning for Face Recognition
Convolutional Neural Networks have reached extremely high performances on the Face Recognition task. Largely used datasets, such as VGGFace2, focus on gender, pose and age variations trying to balance them to achieve better results. However, the fact that images have different resolutions is not usually discussed and resize to 256 pixels before cropping is used. While specific datasets for very low resolution faces have been proposed, less attention has been payed on the task of cross-resolution matching. Such scenarios are of particular interest for forensic and surveillance systems in which it usually happens that a low-resolution probe has to be matched with higher-resolution galleries. While it is always possible to either increase the resolution of the probe image or to reduce the size of the gallery images, to the best of our knowledge an extensive experimentation of cross-resolution matching was missing in the recent deep learning based literature. In the context of low- and cross-resolution Face Recognition, the contributions of our work are: i) we proposed a training method to fine-tune a state-of-the-art model in order to make it able to extract resolution-robust deep features; ii) we tested our models on the benchmark datasets IJB-B/C considering images at both full and low resolutions in order to show the effectiveness of the proposed training algorithm. To the best of our knowledge, this is the first work testing extensively the performance of a FR model in a cross-resolution scenario; iii) we tested our models on the low resolution and low quality datasets QMUL-SurvFace and TinyFace and showed their superior performances, even though we did not train our model on low-resolution faces only and our main focus was cross-resolution; iv) we showed that our approach can be more effective with respect to preprocessing faces with super resolution techniques.
Open AccessCross-Resolution Learning for Face Recognition
Convolutional Neural Networks have reached extremely high performances on the Face Recognition task. Largely used datasets, such as VGGFace2, focus on gender, pose and age variations trying to balance them to achieve better results. However, the fact that images have different resolutions is not usually discussed and resize to 256 pixels before cropping is used. While specific datasets for very low resolution faces have been proposed, less attention has been payed on the task of cross-resolution matching. Such scenarios are of particular interest for forensic and surveillance systems in which it usually happens that a low-resolution probe has to be matched with higher-resolution galleries. While it is always possible to either increase the resolution of the probe image or to reduce the size of the gallery images, to the best of our knowledge an extensive experimentation of cross-resolution matching was missing in the recent deep learning based literature. In the context of low- and cross-resolution Face Recognition, the contributions of our work are: i) we proposed a training method to fine-tune a state-of-the-art model in order to make it able to extract resolution-robust deep features; ii) we tested our models on the benchmark datasets IJB-B/C considering images at both full and low resolutions in order to show the effectiveness of the proposed training algorithm. To the best of our knowledge, this is the first work testing extensively the performance of a FR model in a cross-resolution scenario; iii) we tested our models on the low resolution and low quality datasets QMUL-SurvFace and TinyFace and showed their superior performances, even though we did not train our model on low-resolution faces only and our main focus was cross-resolution; iv) we showed that our approach can be more effective with respect to preprocessing faces with super resolution techniques.
- 2 September 2019
- Published by Springer Nature
- p. 21-29
Improving Multi-scale Face Recognition Using VGGFace2
- 2 September 2019
- Published by Springer Nature
- p. 21-29
Improving Multi-scale Face Recognition Using VGGFace2
- Open Access
- 28 August 2015
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 115 (9) , 091302
Search for Event Rate Modulation in XENON100 Electronic Recoil Data
We have searched for periodic variations of the electronic recoil event rate in the (2–6) keV energy range recorded between February 2011 and March 2012 with the XENON100 detector, adding up to 224.6 live days in total. Following a detailed study to establish the stability of the detector and its background contributions during this run, we performed an unbinned profile likelihood analysis to identify any periodicity up to 500 days. We find a global significance of less than for all periods, suggesting no statistically significant modulation in the data. While the local significance for an annual modulation is , the analysis of a multiple-scatter control sample and the phase of the modulation disfavor a dark matter interpretation. The DAMA/LIBRA annual modulation interpreted as a dark matter signature with axial-vector coupling of weakly interacting massive particles to electrons is excluded at .- 28 August 2015
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 115 (9) , 091302
Open AccessSearch for Event Rate Modulation in XENON100 Electronic Recoil Data
We have searched for periodic variations of the electronic recoil event rate in the (2–6) keV energy range recorded between February 2011 and March 2012 with the XENON100 detector, adding up to 224.6 live days in total. Following a detailed study to establish the stability of the detector and its background contributions during this run, we performed an unbinned profile likelihood analysis to identify any periodicity up to 500 days. We find a global significance of less than for all periods, suggesting no statistically significant modulation in the data. While the local significance for an annual modulation is , the analysis of a multiple-scatter control sample and the phase of the modulation disfavor a dark matter interpretation. The DAMA/LIBRA annual modulation interpreted as a dark matter signature with axial-vector coupling of weakly interacting massive particles to electrons is excluded at .