Search Results - "Migliorati, Andrea"
-
1
Cancelable templates for secure face verification based on deep learning and random projections
Published in EURASIP Journal on Information Security (08-03-2024)“…Recently, biometric recognition has become a significant field of research. The concept of cancelable biometrics (CB) has been introduced to address security…”
Get full text
Journal Article -
2
Gaussian class-conditional simplex loss for accurate, adversarially robust deep classifier training
Published in EURASIP Journal on Information Security (10-03-2023)“…In this work, we present the Gaussian Class-Conditional Simplex (GCCS) loss: a novel approach for training deep robust multiclass classifiers that improves…”
Get full text
Journal Article -
3
Learnable Descriptors for Visual Search
Published in IEEE transactions on image processing (2021)“…This work proposes LDVS, a learnable binary local descriptor devised for matching natural images within the MPEG CDVS framework. LDVS descriptors are learned…”
Get full text
Journal Article -
4
Playing the Lottery With Concave Regularizers for Sparse Trainable Neural Networks
Published in IEEE transaction on neural networks and learning systems (13-03-2024)“…The design of sparse neural networks, i.e., of networks with a reduced number of parameters, has been attracting increasing research attention in the last few…”
Get full text
Journal Article -
5
Beyond cross-entropy: learning highly separable feature distributions for robust and accurate classification
Published in 2020 25th International Conference on Pattern Recognition (ICPR) (10-01-2021)“…Deep learning has shown outstanding performance in several applications including image classification. However, deep classifiers are known to be highly…”
Get full text
Conference Proceeding -
6
Exploring the Potential of Compressive Sensing Payloads for Earth Observation from Geostationary Platforms: An Instrumental Concept for Fire Monitoring
Published in Engineering proceedings (01-11-2023)“…Earth observation (EO) payload performances in the infrared spectral region from geostationary platforms are often limited by spatial resolution. In this…”
Get full text
Journal Article -
7
ConQ: Binary Quantization of Neural Networks via Concave Regularization
Published in 2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP) (22-09-2024)“…The increasing demand for deep neural networks (DNNs) in resource-constrained systems propels the interest in heavily quantized architectures such as networks…”
Get full text
Conference Proceeding -
8
Sparsification of Deep Neural Networks via Ternary Quantization
Published in 2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP) (22-09-2024)“…In recent years, the demand for compact deep neural networks (DNN s) has increased consistently, driven by the necessity to deploy them in environments with…”
Get full text
Conference Proceeding -
9
Onboard Processing Capabilities of an Earth Observation Compressive Sensing Payload
Published in IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium (16-07-2023)“…In this paper, we explore the onboard processing capabilities of an optical Earth observation instrument operating under the principles of compressed sensing,…”
Get full text
Conference Proceeding -
10
Beyond cross-entropy: learning highly separable feature distributions for robust and accurate classification
Published 29-10-2020“…Deep learning has shown outstanding performance in several applications including image classification. However, deep classifiers are known to be highly…”
Get full text
Journal Article -
11
Feature Fusion for Robust Patch Matching with Compact Binary Descriptors
Published in 2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP) (01-08-2018)“…This work addresses the problem of learning compact yet discriminative patch descriptors within a deep learning framework. We observe that features extracted…”
Get full text
Conference Proceeding -
12
Feature Fusion for Robust Patch Matching With Compact Binary Descriptors
Published 11-01-2019“…This work addresses the problem of learning compact yet discriminative patch descriptors within a deep learning framework. We observe that features extracted…”
Get full text
Journal Article