papers

Publications (40)

cs.CV2024

Transformer-based Video Saliency Prediction with High Temporal Dimension Decoding

Morteza Moradi, Simone Palazzo, Concetto Spampinato

In recent years, finding an effective and efficient strategy for exploiting spatial and temporal information has been a hot research topic in video saliency prediction (VSP). With…

cs.LG2022

Transfer without Forgetting

Matteo Boschini, Lorenzo Bonicelli, Angelo Porrello +5

This work investigates the entanglement between Continual Learning (CL) and Transfer Learning (TL). In particular, we shed light on the widespread application of network pretrainin…

cs.CV2016

Gamifying Video Object Segmentation

Simone Palazzo, Concetto Spampinato, Daniela Giordano

Video object segmentation can be considered as one of the most challenging computer vision problems. Indeed, so far, no existing solution is able to effectively deal with the pecul…

cs.CV2025

DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models

Simone Carnemolla, Matteo Pennisi, Sarinda Samarasinghe +5

Understanding and explaining the behavior of machine learning models is essential for building transparent and trustworthy AI systems. We introduce DEXTER, a data-free framework th…

cs.LG2023

A Privacy-Preserving Walk in the Latent Space of Generative Models for Medical Applications

Matteo Pennisi, Federica Proietto Salanitri, Giovanni Bellitto +3

Generative Adversarial Networks (GANs) have demonstrated their ability to generate synthetic samples that match a target distribution. However, from a privacy perspective, using GA…

cs.CV2022

Transforming Image Generation from Scene Graphs

Renato Sortino, Simone Palazzo, Concetto Spampinato

Generating images from semantic visual knowledge is a challenging task, that can be useful to condition the synthesis process in complex, subtle, and unambiguous ways, compared to…

cs.LG2023

FedER: Federated Learning through Experience Replay and Privacy-Preserving Data Synthesis

Matteo Pennisi, Federica Proietto Salanitri, Giovanni Bellitto +4

In the medical field, multi-center collaborations are often sought to yield more generalizable findings by leveraging the heterogeneity of patient and clinical data. However, recen…

q-bio.NC2024

QuantFormer: Learning to Quantize for Neural Activity Forecasting in Mouse Visual Cortex

Salvatore Calcagno, Isaak Kavasidis, Simone Palazzo +8

Understanding complex animal behaviors hinges on deciphering the neural activity patterns within brain circuits, making the ability to forecast neural activity crucial for developi…

cs.CV2024

MatFuse: Controllable Material Generation with Diffusion Models

Giuseppe Vecchio, Renato Sortino, Simone Palazzo +1

Creating high-quality materials in computer graphics is a challenging and time-consuming task, which requires great expertise. To simplify this process, we introduce MatFuse, a uni…

cs.CV2020

Correct block-design experiments mitigate temporal correlation bias in EEG classification

Simone Palazzo, Concetto Spampinato, Joseph Schmidt +3

It is argued in [1] that [2] was able to classify EEG responses to visual stimuli solely because of the temporal correlation that exists in all EEG data and the use of a block desi…

cs.CV2023

A baseline on continual learning methods for video action recognition

Giulia Castagnolo, Concetto Spampinato, Francesco Rundo +2

Continual learning has recently attracted attention from the research community, as it aims to solve long-standing limitations of classic supervisedly-trained models. However, most…

cs.LG2023

On the Effectiveness of Equivariant Regularization for Robust Online Continual Learning

Lorenzo Bonicelli, Matteo Boschini, Emanuele Frascaroli +6

Humans can learn incrementally, whereas neural networks forget previously acquired information catastrophically. Continual Learning (CL) approaches seek to bridge this gap by facil…

cs.LG2022

Effects of Auxiliary Knowledge on Continual Learning

Giovanni Bellitto, Matteo Pennisi, Simone Palazzo +4

In Continual Learning (CL), a neural network is trained on a stream of data whose distribution changes over time. In this context, the main problem is how to learn new information…

eess.IV2021

An Explainable AI System for Automated COVID-19 Assessment and Lesion Categorization from CT-scans

Matteo Pennisi, Isaak Kavasidis, Concetto Spampinato +12

COVID-19 infection caused by SARS-CoV-2 pathogen is a catastrophic pandemic outbreak all over the world with exponential increasing of confirmed cases and, unfortunately, deaths. I…

cs.CV2024

AIM 2024 Challenge on Video Saliency Prediction: Methods and Results

Andrey Moskalenko, Alexey Bryncev, Dmitry Vatolin +30

This paper reviews the Challenge on Video Saliency Prediction at AIM 2024. The goal of the participants was to develop a method for predicting accurate saliency maps for the provid…

astro-ph.IM2024

Self-supervised learning for radio-astronomy source classification: a benchmark

Thomas Cecconello, Simone Riggi, Ugo Becciani +5

The upcoming Square Kilometer Array (SKA) telescope marks a significant step forward in radio astronomy, presenting new opportunities and challenges for data analysis. Traditional…

cs.CV2024

SalFoM: Dynamic Saliency Prediction with Video Foundation Models

Morteza Moradi, Mohammad Moradi, Francesco Rundo +3

Recent advancements in video saliency prediction (VSP) have shown promising performance compared to the human visual system, whose emulation is the primary goal of VSP. However, cu…

cs.CV2023

MeT: A Graph Transformer for Semantic Segmentation of 3D Meshes

Giuseppe Vecchio, Luca Prezzavento, Carmelo Pino +3

Polygonal meshes have become the standard for discretely approximating 3D shapes, thanks to their efficiency and high flexibility in capturing non-uniform shapes. This non-uniformi…

cs.CV2024

Evidential Federated Learning for Skin Lesion Image Classification

Rutger Hendrix, Federica Proietto Salanitri, Concetto Spampinato +2

We introduce FedEvPrompt, a federated learning approach that integrates principles of evidential deep learning, prompt tuning, and knowledge distillation for distributed skin lesio…

cs.CV2019

Deep Learning Human Mind for Automated Visual Classification

Concetto Spampinato, Simone Palazzo, Isaak Kavasidis +3

What if we could effectively read the mind and transfer human visual capabilities to computer vision methods? In this paper, we aim at addressing this question by developing the fi…

cs.LG2024

FedRewind: Rewinding Continual Model Exchange for Decentralized Federated Learning

Luca Palazzo, Matteo Pennisi, Federica Proietto Salanitri +3

In this paper, we present FedRewind, a novel approach to decentralized federated learning that leverages model exchange among nodes to address the issue of data distribution shift.…

cs.CV2022

Neural Transformers for Intraductal Papillary Mucosal Neoplasms (IPMN) Classification in MRI images

Federica Proietto Salanitri, Giovanni Bellitto, Simone Palazzo +9

Early detection of precancerous cysts or neoplasms, i.e., Intraductal Papillary Mucosal Neoplasms (IPMN), in pancreas is a challenging and complex task, and it may lead to a more f…

cs.CV2018

Top-Down Saliency Detection Driven by Visual Classification

Francesca Murabito, Concetto Spampinato, Simone Palazzo +2

This paper presents an approach for top-down saliency detection guided by visual classification tasks. We first learn how to compute visual saliency when a specific visual task has…

cs.AI2026

OCCAM: Open-set Causal Concept explAnation and Ontology induction for black-box vision Models

Chiara Maria Russo, Simone Carnemolla, Simone Palazzo +3

Interpreting the decisions of deep image classifiers remains challenging, particularly in black-box settings where model internals are inaccessible. We introduce OCCAM, a framework…

eess.IV2021

Hierarchical 3D Feature Learning for Pancreas Segmentation

Federica Proietto Salanitri, Giovanni Bellitto, Ismail Irmakci +3

We propose a novel 3D fully convolutional deep network for automated pancreas segmentation from both MRI and CT scans. More specifically, the proposed model consists of a 3D encode…

cs.RO2022

MIDGARD: A Simulation Platform for Autonomous Navigation in Unstructured Environments

Giuseppe Vecchio, Simone Palazzo, Dario C. Guastella +4

We present MIDGARD, an open-source simulation platform for autonomous robot navigation in outdoor unstructured environments. MIDGARD is designed to enable the training of autonomou…

cs.CV2024

Diffexplainer: Towards Cross-modal Global Explanations with Diffusion Models

Matteo Pennisi, Giovanni Bellitto, Simone Palazzo +2

We present DiffExplainer, a novel framework that, leveraging language-vision models, enables multimodal global explainability. DiffExplainer employs diffusion models conditioned on…

cs.CV2021

SurfaceNet: Adversarial SVBRDF Estimation from a Single Image

Giuseppe Vecchio, Simone Palazzo, Concetto Spampinato

In this paper we present SurfaceNet, an approach for estimating spatially-varying bidirectional reflectance distribution function (SVBRDF) material properties from a single image.…

cs.CV2020

Domain Adaptation for Outdoor Robot Traversability Estimation from RGB data with Safety-Preserving Loss

Simone Palazzo, Dario C. Guastella, Luciano Cantelli +5

Being able to estimate the traversability of the area surrounding a mobile robot is a fundamental task in the design of a navigation algorithm. However, the task is often complex,…

cs.CV2023

TinyHD: Efficient Video Saliency Prediction with Heterogeneous Decoders using Hierarchical Maps Distillation

Feiyan Hu, Simone Palazzo, Federica Proietto Salanitri +4

Video saliency prediction has recently attracted attention of the research community, as it is an upstream task for several practical applications. However, current solutions are p…

cs.LG2026

Dream2Learn: Structured Generative Dreaming for Continual Learning

Salvatore Calcagno, Matteo Pennisi, Federica Proietto Salanitri +4

Continual learning requires balancing plasticity and stability while mitigating catastrophic forgetting. Inspired by human dreaming as a mechanism for internal simulation and knowl…

cs.CV2023

Transformer-based Image Generation from Scene Graphs

Renato Sortino, Simone Palazzo, Concetto Spampinato

Graph-structured scene descriptions can be efficiently used in generative models to control the composition of the generated image. Previous approaches are based on the combination…

cs.CV2021

Hierarchical Domain-Adapted Feature Learning for Video Saliency Prediction

Giovanni Bellitto, Federica Proietto Salanitri, Simone Palazzo +3

In this work, we propose a 3D fully convolutional architecture for video saliency prediction that employs hierarchical supervision on intermediate maps (referred to as conspicuity…

cs.CV2026

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

Morteza Moradi, Mohammad Moradi, Simone Palazzo +2

Salient Object Detection (SOD) remains an essential yet underexplored task in the era of large-scale vision models. Although foundation models like SAM exhibit strong generalizatio…

cs.CV2024

Selective Attention-based Modulation for Continual Learning

Giovanni Bellitto, Federica Proietto Salanitri, Matteo Pennisi +5

We present SAM, a biologically-plausible selective attention-driven modulation approach to enhance classification models in a continual learning setting. Inspired by neurophysiolog…

cs.SD2025

SeeingSounds: Learning Audio-to-Visual Alignment via Text

Simone Carnemolla, Matteo Pennisi, Chiara Russo +3

We introduce SeeingSounds, a lightweight and modular framework for audio-to-image generation that leverages the interplay between audio, language, and vision-without requiring any…

cs.LG2024

Back to Supervision: Boosting Word Boundary Detection through Frame Classification

Simone Carnemolla, Salvatore Calcagno, Simone Palazzo +1

Speech segmentation at both word and phoneme levels is crucial for various speech processing tasks. It significantly aids in extracting meaningful units from an utterance, thus ena…

cs.NE2023

Wake-Sleep Consolidated Learning

Amelia Sorrenti, Giovanni Bellitto, Federica Proietto Salanitri +3

We propose Wake-Sleep Consolidated Learning (WSCL), a learning strategy leveraging Complementary Learning System theory and the wake-sleep phases of the human brain to improve the…

cs.CV2020

Decoding Brain Representations by Multimodal Learning of Neural Activity and Visual Features

Simone Palazzo, Concetto Spampinato, Isaak Kavasidis +3

This work presents a novel method of exploring human brain-visual representations, with a view towards replicating these processes in machines. The core idea is to learn plausible…

cs.CV2026

UNBOX: Unveiling Black-box visual models with Natural-language

Simone Carnemolla, Chiara Russo, Simone Palazzo +5

Ensuring trustworthiness in open-world visual recognition requires models that are interpretable, fair, and robust to distribution shifts. Yet modern vision systems are increasingl…