CV
Education
Politecnico di Milano, Milan, Italy
PhD in Computer Science and Engineering (November 2021 - April 2025)
- Thesis: Few Shot Segmentation to Combat Data Drought in Precision Agriculture
- Advisor: Prof. Matteo Matteucci
Eötvös Loránd University, Budapest, Hungary
MSc in Computer Science for Autonomous Systems (August 2019 - June 2021)
- Thesis: Gaze-Based Social Region of Interest Detection of Humans
- Advisor: Prof. András Lőrincz
Kungliga Tekniska Högskolan (KTH), Stockholm, Sweden
MSc in Computer Science for Autonomous Systems (August 2019 - June 2021)
- Minor in Entrepreneurship
Politecnico di Milano, Milan, Italy
BSc in Computer Science and Engineering (September 2016 - March 2020)
Research Interests
My research focuses on Artificial Intelligence, Robotics, and Autonomous Systems, with an emphasis on Computer Vision. Specifically, I explore:
- Few-Shot Segmentation & Domain Adaptation: Developing methods to improve segmentation performance with minimal supervision, particularly for agricultural robotics.
- Vision Transformer Analysis: Investigating ViT latent spaces for FSS and semantic segmentation using prototypical learning.
- Multimodal Large Language Models: Integrating textual information with computer vision for segmentation and video understanding tasks.
Publications
Published
- Balancing Accuracy and Cost in Precision Agriculture: A Few-Shot Learning Approach for Efficient Weed-Crop Segmentation. Nico Catalano, Sofia Matilde Luglio, Agnese Chiatti, Mino Sportelli, Christian Frasconi, Davide Facchinetti, Matteo Matteucci. Computers and Electronics in Agriculture 2026.
- MARS: a multimodal alignment and ranking system for few-shot segmentation. Nico Catalano, Stefano Samele, Paolo Pertino, Matteo Matteucci. WACV 2026.
- Differentiable Hierarchical Visual Tokenization. Marius Aasan, Martine Hjelkrem-Tan, Nico Catalano, Changkyu Choi, Adín Ramírez Rivera. NeurIPS 2025.
- Graph Against the Machine: Neuro-Symbolic Approach for Enhanced Video Question Answering. Fabio Lusha, Agnese Chiatti, Sara Pidò, Nico Catalano, Matteo Matteucci. Workshop of ECAI 2025.
- Tackling Environmental Variability: Few Shot Segmentation for Domain-Adaptive Weed Segmentation in Agricultural Robotics. Nico Catalano, Monica Leone, Matteo Matteucci. CASE 2024.
- More than the Sum of Its Parts: Ensembling Backbone Networks for Few-Shot Segmentation Nico Catalano, Alessandro Maranelli, Agnese Chiatti, Matteo Matteucci. IJCNN 2024.
- Surgical Fine-Tuning for Grape Bunch Segmentation Under Visual Domain Shifts. Agnese Chiatti, Riccardo Bertoglio, Nico Catalano, Matteo Gatti, Matteo Matteucci. ECMR 2023.
- A comparative study of Fourier transform and CycleGAN as domain adaptation techniques for weed segmentation Riccardo Bertoglio, Alessio Mazzucchelli, Nico Catalano, Matteo Matteucci. Smart Agricultural Technology, 2023.
Under Review / Preprints
- Nico Catalano, Matteo Matteucci. Few Shot Semantic Segmentation: A Review of Methodologies, Benchmarks, and Open Challenges. arXiv:2304.05832.
Teaching Experience
- Fall 2025: Fundamentals of Computer Science, Laboratory Assistant
- Fall 2025: Deep Learning for Computer Vision, Teaching Assistant
- Fall 2024: Fundamentals of Computer Science, Laboratory Assistant
- Fall 2023: Fundamentals of Computer Science, Laboratory Assistant
- Spring 2022: Game Development, Laboratory Assistant
- Fall 2022: Fundamentals of Computer Science, Laboratory Assistant
Thesis Mentoring
- 2026 - Present: Improving Fine Grained Reasoning in VLM – Matteo Bernardi
- 2026 - Present: Improve Segmentation Models using a VLM – Daniele Spini
- 2026 - Present: Following Temporal Graph Traces in Videos – Donald Gera
- 2025 - Present: Multimodal Few Shot Segmentation in Videos – Michele Cavicchioli
- 2025 - 2026: Training Vision Tasks Using Diagnostic Text Description Loss – Luca Olivieri
- 2024 - 2025: Understanding Video Content with Multimodal Large Language Models and Graphs – Fabio Lusha
- 2024 - 2025: Visual Foundation Model for Few-Shot Segmentation and Anomaly Detection – Paolo Pertino
- 2023: Enhancing Agricultural Image Embeddings for Detecting Weeds in Few-Shot Segmentation – Alessandro Maranelli
- 2022 - 2023: The Devil is in the Details: A Few-Shot Approach for Small Weeds Segmentation – Monica Leone
- 2022 - 2023: A Semi-Automatic Tool for Instance Segmentation – Maximilian Fehrentz
Outreach & Professional Development
Visiting Period
- March 2024 - June 2024: University of Oslo, Digital Signal Processing and Image Analysis Lab
- Collaboration with Prof. Adín Ramírez Rivera on Vision Transformer latent space analysis for segmentation tasks.
Tool Development
- Developed a semi-automatic segmentation tool for grape labeling using domain-adaptive segmentation models.
Academic Reviews
- Journals: IEEE Access, IEEE Transactions on Circuits and Systems for Video Technology, IEEE/CAA Journal of Automatica Sinica, Springer Nature The Visual Computer, PLOS ONE.
- Conferences: IEEE International Conference on Automation Science and Engineering (CASE).
Technical Skills
Programming Languages
- Python, C++, Matlab, Java, C
Frameworks & Libraries
- PyTorch, OpenCV, ROS
Languages
- Italian: Native
- English: IELTS Score: 7
Work Experience
Research Intern
- Sztaki, Budapest, Hungary (Feb 2021 – May 2021)
- Developed computer vision algorithms for pedestrian safety in autonomous driving.
Software Developer
- Tesi Informatica SRL, Casalmoro, Italy (Dec 2014 – May 2016)
- Worked on system integration, Android development, web services, and MySQL databases.