Concetto Spampinato

DAS-SPP: Transformer-based seismic phase picking on distributed acoustic sensing data

Miriana Corsaro, Flavio Cannavò, Gilda Currenti, Philippe Jousset et autres

Advanced deep learning techniques are opening up new possibilities for seismic monitoring using distributed acoustic sensing (DAS) technology. In this study, we present a lightweight Transformer-U-Net architecture that combines the fine-grained spatial resolution of U-Net with the global contextual modeling capabilities of …

it, de (code pays fourni par la source)

FedCMAPSS: A Benchmark for Federated Learning in Remaining Useful Life Estimation

Amelia Sorrenti, Matteo Pennisi, Concetto Spampinato, Simone Palazzo

Data-driven prognostics and health management has emerged as a key enabler for Industry 4.0, yet the development of robust remaining useful life (RUL) estimation models is often limited by the scarcity of run-to-failure data. While federated learning offers a promising paradigm to …

Retrieval-Augmented Visual Prompting: Guiding Foundation Models in Two-Photon Imaging

Salvatore Calcagno, Marco Finocchiaro, Giovanni Bellitto, Daniela Giordano et autres

Two-photon calcium imaging presents a challenging setting for foundation models: image appearance varies substantially across recordings and experimental conditions, annotations are scarce, and rapid adaptation is often needed. Rather than adapting model weights through fine-tuning, we ask whether a foundation model can …

Global–Local Feature Decoding with Adapter-Guided SAMv2 for Salient Object Detection

Morteza Moradi, Mohammad Moradi, Simone Palazzo, Ali Borji et autres

it (code pays fourni par la source)

Dream2Learn: Structured Generative Dreaming for Continual Learning

Salvatore Calcagno, Matteo Pennisi, Federica Proietto Salanitri, Amelia Sorrenti et autres

Abstract Continual learning requires balancing plasticity and stability while mitigating catastrophic forgetting. Inspired by the concept of human dreaming as a source of internal simulation and knowledge restructuring, we introduce Dream2Learn (D2L) , a framework in which a continual classifier leverages its …

it (code pays fourni par la source)

AI-based predictive biomarkers for chronic neurological diseases: the rAIdD prospective, multicenter, observational study protocol

Simone Varrasi, Alfredo Pulvirenti, Vincenzo Catania, Maurizio Palesi et autres

Background Chronic neurological disorders such as Multiple Sclerosis (MS), Parkinson's disease (PD), and Alzheimer's Disease (AD) represent a major global health burden characterized by progressive neurodegeneration, functional disability, and cognitive decline. Despite differences in etiology and clinical presentation, these conditions share multifactorial …

it, lb, ru, kr (code pays fourni par la source)

A Multi-Center Benchmark for Abdominal Disease Diagnosis and Report Generation from Non-Contrast CT

Mariam Elbakry, Aliaa Sayed Sheha, Salma Hassan Tantawy, Aya Yassin et autres

Multiphasic contrast-enhanced CT (CECT) is widely used for abdominal lesion characterization, yet it carries inherent risks of contrast-induced nephropathy, escalates acquisition burden, and heavily contributes to radiologist workload. To address these challenges, we introduce a novel multi-center benchmark for multi-organ abdominal disease …

TrustErase: Auditable Instant Machine Unlearning with Passport-Embedded Representations

Rutger Hendrix, Leonardo G. Russo, Concetto Spampinato, Matteo Pennisi et autres

The demand for privacy-compliant AI has amplified the need for machine unlearning; yet, existing retraining or distillation-based methods remain unverifiable and computationally costly. We introduce TrustErase, a verifiable, data-free unlearning framework leveraging passport-embedded representations for instant, modular, and auditable forgetting. By treating …

A Multi-Center Benchmark for Abdominal Disease Diagnosis and Report Generation from Non-Contrast CT

Mariam Elbakry, Aliaa Sayed Sheha, Salma Hassan Tantawy, Aya Yassin et autres

Multiphasic contrast-enhanced CT (CECT) is widely used for abdominal lesion characterization, yet it carries inherent risks of contrast-induced nephropathy, escalates acquisition burden, and heavily contributes to radiologist workload. To address these challenges, we introduce a novel multi-center benchmark for multi-organ abdominal disease …

Égypte, it, es, hk (code pays fourni par la source)

TrustErase: Auditable Instant Machine Unlearning with Passport-Embedded Representations

Rutger Hendrix, Leonardo G. Russo, Concetto Spampinato, Matteo Pennisi et autres

The demand for privacy-compliant AI has amplified the need for machine unlearning; yet, existing retraining or distillation-based methods remain unverifiable and computationally costly. We introduce TrustErase, a verifiable, data-free unlearning framework leveraging passport-embedded representations for instant, modular, and auditable forgetting. By treating …

it (code pays fourni par la source)

Real-Time Seismic Monitoring Using DAS and AI

Miriana Corsaro, Gilda Currenti, Flavio Cannavò, Martina Allegra et autres

Seismic monitoring in active volcanic areas requires systems capable of providing high spatial and temporal resolution, in order to capture the complex and rapidly evolving dynamics of such environments. In this context, the reuse of existing telecommunications infrastructure through distributed acoustic sensing …

fr, it, at (code pays fourni par la source)

Leveraging deep learning for denoising DAS recordings in urban volcanic areas

Martina Allegra, Flavio Cannavò, Gilda Currenti, Miriana Corsaro et autres

Distributed Acoustic Sensing (DAS) has emerged as a transformative technology in the field of geophysics. Among its notable advantages stands out the ability to leverage existing fibre-optic telecommunications infrastructure to obtain high-quality seismic recordings with unprecedented spatial and temporal resolution. This feature …