Thesis Details

Computer Vision with Active Learning

Ph.D. Thesis Student: Kolář Martin Academic Year: 2021/2022 Supervisor: Zemčík Pavel, prof. Dr. Ing.
Czech title
Počítačové vidění s aktivním učením

Machine Vision methods benefit from improving models, tuning trained parameters, or labeling representative data. In a series of experiments, this work validates the hypothesis that Active Learning improves the accuracy of these models. By extending the pseudolabel framework to Active Learning, this work includes a One-shot-learning approach to learn novel image categories by utilising an algorithmic recommender, an online Graphical User Interface to optimise the online Exploration/Exploitation tradeoff for tagging, and a two-step offline binary Active Learning framework to improve the quality of data used for Font Capture. By demonstrating the benefit of Active Learning in these approaches, this work contributes to the hypothesis, as well as concrete Machine Vision applications.


Computer Vision, Object Classification, Semi-supervised Learning, Active Learning, Transfer Learning

Degree Programme
Computer Science and Engineering, Field of Study Computer Science and Engineering
24 February 2022
KOLÁŘ, Martin. Computer Vision with Active Learning. Brno, 2021. Ph.D. Thesis. Brno University of Technology, Faculty of Information Technology. 2022-02-24. Supervised by Zemčík Pavel. Available from:
    author = "Martin Kol\'{a}\v{r}",
    type = "Ph.D. thesis",
    title = "Computer Vision with Active Learning",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2022,
    location = "Brno, CZ",
    language = "english",
    url = ""
Back to top