Hey there! I'm Francesco Pelosin, I'm Italian and I'm from Bassano del Grappa (north-east). I recently got a
Ph.D. (july 2022) from Ca' Foscari University of Venice where I focused my studies on Continual Learning for
Computer Vision. If you need to contact me, drop an e-mail here: pelosinf[at]gmail
. Uh oh...lastly: I
still consider myself an script k1ddie :D
My path of studies/work π
2018 | B.Sc + M.Sc. in Computer Science - Data Management and Analytics | Ca' Foscari University | Venice, Italy |
2018-2022 | Ph.D. in Artificial Intelligence (Prof. Andrea Torsello) | Ca' Foscari University | Venice, Italy |
↪ 9 months | Visiting Researcher, LAMP group (PI Joost Van De Weijer) | Computer Vision Center (CVC) | Barcelona, Spain |
2022-2023 | AI Research Fellow | Leonardo s.p.a. | Rome, Italy | 2023-now | Computer Vision/Machine Learning Engineer | Covision Lab | Brixen - South Tyrol, Italy |
My research interests π¬
★Continual Learning |
★Semantic Segmentation |
★Computer Vision |
My skills π
Python | β°β°β°β°β°β± |
Pytorch / opencv / sklearn | β°β°β°β°β°β± |
matplotlib / streamlit / pandas | β°β°β°β°β°β± |
git / docker / bash | β°β°β°β°β±β± |
C++ / C / Java / x86 | β°β°β°β±β±β± |
Introduzione Unsupervised Learning | ➟ | IPython Notebook with exercices (in Italian) |
Geospatial data wrangling | ➟ | IPython Notebook with exercices (in Italian) |
Tutorato di architettura degli elaboratori | ➟ | YouTube Video Lectures (in Italian) |
Dynamic Label Injection for Imbalanced Industrial Defect Segmentation
VISION Workshop (ECCV 2024)
π» code | π pdf | π cite
@inproceedings{caruso2024dynamic, title={Dynamic Label Injection for Imbalanced Industrial Defect Segmentation}, author={Caruso, Emanuele and Pelosin, Francesco and Simoni, Alessandro and Boschetti, Marco}, booktitle={Proceedings of the European Conference on Computer Vision Workshops}, year={2024} }
DUCK: Distance-based Unlearning via Centroid Kinematics
... submitted ... (WACV 2025)
π» code | π pdf | π cite
@misc{cotogni2023duck, title={DUCK: Distance-based Unlearning via Centroid Kinematics}, author={Marco Cotogni and Jacopo Bonato and Luigi Sabetta and Francesco Pelosin and Alessandro Nicolosi}, year={2023}, eprint={2312.02052}, archivePrefix={arXiv}, primaryClass={cs.CV} }
MIND: Multi-Task Incremental Network Distillation
AAAI (2024)
π» code | π pdf | π cite
@misc{mind2024, author={Bonato, Jacopo and Pelosin, Francesco and Sabetta, Luigi and Nicolosi, Alessandro}, title = {MIND: Multi-Task Incremental Network Distillation}, publisher = AAAI Conference on Artificial Intelligence (AAAI 2024), year = {2024}, }
Simpler Is Better: off-the-shelf Continual Learning Through Pretrained Backbones
Workshop T4V (CVPR 2022)
π» code | π pdf | π cite
@misc{pelosin2022simpler, author = {Pelosin, Francesco}, title = {Simpler is Better: off-the-shelf Continual Learning Through Pretrained Backbones}, publisher = Transformers 4 Vision Workshop (CVPR 2022), year = {2022}, }
Towards Exemplar-Free Continual Learning in Vision Transformers: an Account of Attention, Functional and Weight Regularization
Workshop CLVISION (CVPR 2022) - Runner-Up Best Paper Award
π» code | π pdf | π cite
@inproceedings{pelosin2022towards, title={Towards exemplar-free continual learning in vision transformers: an account of attention, functional and weight regularization}, author={Pelosin, Francesco and Jha, Saurav and Torsello, Andrea and Raducanu, Bogdan and van de Weijer, Joost}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, booksubtitle={Workshop on Continual Learning}, pages={3820--3829}, year={2022} }
Smaller is Better: An Analysis of Instance Quantity/Quality Trade-off in Rehearsal-based Continual Learning
IJCNN (2022)
π» code | π pdf | π cite
@misc{pelosin2021better, title={Smaller Is Better: An Analysis of Instance Quantity/Quality Trade-off in Rehearsal-based Continual Learning}, author={Francesco Pelosin and Andrea Torsello}, year={2022}, book={IJCNN} }
Unsupervised semantic discovery through visual patterns detection
S+SSPR (2022)
π» code | π pdf | π cite
@article{DBLP:journals/corr/abs-2102-12213, author = {Francesco Pelosin and Andrea Gasparetto and Andrea Albarelli and Andrea Torsello}, title = {Unsupervised semantic discovery through visual patterns detection}, journal = {S+SSPR}, year = {2021}, }
Separating Structure from Noise in Large Graphs Using the Regularity Lemma
Pattern Recognition (2020)
π» code | π pdf | π cite
@article{FIORUCCI2020107070, title = {Separating Structure from Noise in Large Graphs Using the Regularity Lemma}, journal = {Pattern Recognition}, volume = {98}, pages = {107070}, year = {2020}, issn = {0031-3203}, doi = {https://doi.org/10.1016/j.patcog.2019.107070}, url = {https://www.sciencedirect.com/science/article/pii/S0031320319303711}, author = {Marco Fiorucci and Francesco Pelosin and Marcello Pelillo}, keywords = {Regularity lemma, Graph summarization, Structural patterns, Noise, Randomness, Graph similarity search}, abstract = {How can we separate structural information from noise in large graphs? To address this fundamental question, we propose a graph summarization approach based on SzemerΓ©diβs Regularity Lemma, a well-known result in graph theory, which roughly states that every graph can be approximated by the union of a small number of random-like bipartite graphs called βregular pairsβ. Hence, the Regularity Lemma provides us with a principled way to describe the essential structure of large graphs using a small amount of data. Our paper has several contributions: (i) We present our summarization algorithm which is able to reveal the main structural patterns in large graphs. (ii) We discuss how to use our summarization framework to efficiently retrieve from a database the top-k graphs that are most similar to a query graph. (iii) Finally, we evaluate the noise robustness of our approach in terms of the reconstruction error and the usefulness of the summaries in addressing the graph search task.} }
Graph Compression Using The Regularity Method
arxiv (2019) M.Sc. Thesis
π» code | π pdf | π cite
@article{DBLP:journals/corr/abs-1810-07275, author = {Francesco Pelosin}, title = {Graph Compression Using The Regularity Method}, journal = {CoRR}, volume = {abs/1810.07275}, year = {2018}, url = {http://arxiv.org/abs/1810.07275}, eprinttype = {arXiv}, eprint = {1810.07275}, timestamp = {Tue, 30 Oct 2018 20:39:56 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1810-07275.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
* . . . . . * *. * * * . . . * * . * lakj