whoami

Hi! I'm Francesco, I live in Italy, and I got a Ph.D. (July 2022) from Ca' Foscari University of Venice, where I focused on Continual Learning for Computer Vision. I like building practical tools, shipping research prototypes, and turning papers into working systems!

Interests

├─ 🧠 Continual Learning
├─ 🧩 Semantic Segmentation
├─ 🎨 Diffusion Models
├─ 🏭 Industrial Vision
└─ ⚙️ ML Engineering

If you need to contact me, email me at pelosinf[at]gmail.

Timeline

2018
M.Sc. in Computer Science (Data Management & Analytics)
Ca' Foscari University · Venice, Italy
2018–2022
Ph.D. in Artificial Intelligence
Ca' Foscari University · Venice, Italy · Advisor: Prof. Andrea Torsello
9 months
Visiting Researcher (LAMP group)
Computer Vision Center (CVC) · Barcelona, Spain · PI: Joost Van De Weijer
2022–2023
Research Scientist
Leonardo s.p.a. · Rome, Italy
2023–now
Deep Learning and Research Engineer
Covision Lab · Brixen (South Tyrol), Italy

Projects

PodXiv - AI-Powered Academic Podcast Generator

Transform arXiv papers into engaging podcast conversations with AI-generated virtual hosts.

🚀 Live Demo

Sample generated from the SAM 2 paper.

ngas-pytorch banner preview

ngas-pytorch

PyTorch library for Neural Gas models and training workflows, introducing differentiable versions of the algorithms.

GitHub
Neural Gas playground preview

Neural Gas Playground

Interactive browser-based playground for exploring the Neural Gas algorithm and prototype adaptation dynamics.

🚀 Live Demo

Publications

* indicates shared first authorship

Preview for Training-Free Fine-Grained Semantic Segmentations in Low Data Regimes: A FungiTastic Baseline

Training-Free Fine-Grained Semantic Segmentations in Low Data Regimes: A FungiTastic Baseline

Sebastian Cavada, Francesco Pelosin, Lapo Faggi

13th Workshop on Fine-Grained Visual Categorization (CVPR 2026)

📄 PDF
Preview for Bounding Box-Guided Diffusion for Synthesizing Industrial Images and Segmentation Maps

Bounding Box-Guided Diffusion for Synthesizing Industrial Images and Segmentation Maps

Alessandro Simoni*, Francesco Pelosin*

Synthetic Data for Computer Vision Workshop (CVPR 2025)

💻 Code 📄 PDF
Preview for Dynamic Label Injection for Imbalanced Industrial Defect Segmentation

Dynamic Label Injection for Imbalanced Industrial Defect Segmentation

Emanuele Caruso*, Francesco Pelosin*, Alessandro Simoni*, Marco Boschetti

VISION Workshop (ECCV 2024)

💻 Code 📄 PDF
Preview for DUCK: Distance-based Unlearning via Centroid Kinematics

DUCK: Distance-based Unlearning via Centroid Kinematics

Marco Cotogni*, Jacopo Bonato*, Luigi Sabetta*, Francesco Pelosin, Alessandro Nicolosi

Under Revision

💻 Code 📄 PDF
Preview for MIND: Multi-Task Incremental Network Distillation

MIND: Multi-Task Incremental Network Distillation

Jacopo Bonato*, Francesco Pelosin*, Luigi Sabetta*, Alessandro Nicolosi

AAAI (2024) Oral

💻 Code 📄 PDF
Preview for Simpler Is Better: off-the-shelf Continual Learning Through Pretrained Backbones

Simpler Is Better: off-the-shelf Continual Learning Through Pretrained Backbones

Francesco Pelosin

Workshop T4V (CVPR 2022)

💻 Code 📄 PDF
Preview for Towards Exemplar-Free Continual Learning in Vision Transformers: an Account of Attention, Functional and Weight Regularization

Towards Exemplar-Free Continual Learning in Vision Transformers: an Account of Attention, Functional and Weight Regularization

Francesco Pelosin*, Saurav Jha*, Andrea Torsello, Bogdan Raducanu, Joost van de Weijer

Workshop CLVISION (CVPR 2022) Runner-Up Best Paper Award

💻 Code 📄 PDF
Preview for Smaller is Better: An Analysis of Instance Quantity/Quality Trade-off in Rehearsal-based Continual Learning

Smaller is Better: An Analysis of Instance Quantity/Quality Trade-off in Rehearsal-based Continual Learning

Francesco Pelosin, Andrea Torsello

IJCNN (2022)

💻 Code 📄 PDF
Preview for Unsupervised semantic discovery through visual patterns detection

Unsupervised semantic discovery through visual patterns detection

Francesco Pelosin, Andrea Gasparetto, Andrea Albarelli, Andrea Torsello

S+SSPR (2022)

💻 Code 📄 PDF
Preview for Separating Structure from Noise in Large Graphs Using the Regularity Lemma

Separating Structure from Noise in Large Graphs Using the Regularity Lemma

Marco Fiorucci, Francesco Pelosin, Marcello Pelillo

Pattern Recognition (2020)

💻 Code 📄 PDF
Preview for Graph Compression Using The Regularity Method

Graph Compression Using The Regularity Method

Francesco Pelosin

arXiv (2019), M.Sc. Thesis

💻 Code 📄 PDF

Recent