Paweł Majewski

Paweł Majewski is a researcher at the Department of Computer Systems and Networks within the Faculty of Computer Science and Telecommunications at Wrocław University of Science and Technology. He is an active member of the Advanced Data Analysis Methods Team (ZZMAD) and conducts research at the intersection of machine learning, computer vision, and precision agriculture applications.

Dr. Majewski completed his doctoral studies with a dissertation titled "Machine Learning Methods for Phenotyping Insect Biosystems, as Exemplified by Honeybees and Mealworms," supervised by Professor Robert Burduk and Professor Jacek Reiner. His doctoral research addressed significant challenges in biological system analysis including time-varying data acquisition conditions, dense scenes, and limited representative datasets.

His research spans several key technical domains:

• Computer vision techniques for biological system analysis
• Semi-supervised and unsupervised anomaly detection methods
• Instance and semantic segmentation applications
• Precision agriculture and precision breeding technologies
• Machine learning approaches for phenotyping insect biosystems

Dr. Majewski has received recognition for his interdisciplinary work:

• Scholarship of the Mayor of Wrocław (2023), awarded to 24 outstanding doctoral students in Wrocław
• Jan Mozrzymas Scholarship for outstanding achievements in interdisciplinary research
• Visegrad Fund scholarship enabling research at National Taiwan University's Biophotonics and Bioimaging Laboratory

His practical contributions include developing solutions in collaboration with the Machine Vision Laboratory (MVLab) that are already supporting agricultural growers and increasing production efficiency. During his doctoral studies, he completed an international internship at National Taiwan University under Professor Ta-Te Lin, working with one of the world's leading teams in precision agriculture research.

As a member of ZZMAD, Dr. Majewski contributes to multiple research initiatives including "Dark-Box Optimization" and evolutionary methods for multi-criteria optimization. His work exemplifies the translation of theoretical machine learning advancements into practical agricultural applications with real-world impact.