Florian Buckermann, M.Sc.

Chair of Data Science (Informatik X)
University of Würzburg
Am Hubland
97074 Würzburg
Germany

Email: buckermann[at]informatik.uni-wuerzburg.de

Phone: (+49 931) 31 - 84898

Office: Room B104 (Computer Science Building M2)

Projects and Research Interests

I joined the Data Science group in December 2019 as a research assistant. Prior, I studied Intelligent Systems (M.Sc.) at Bielefeld University. Up to now, my main research interests have been machine learning and image processing. Recently, I focused on using deep learning for semantic segmentation.

As a member of the AI@Knauf project, I am researching the potential integration of machine learning methods into a manufacturing process.

Teaching

Data Mining (summer term 2021, 2022)
Praktikum "Machine Learning for Time Series Analysis" (summer term 2021)
Seminar "Selected Chapters from Machine Learning" (winter term 2020, summer term 2020)

Publications

Semi-unsupervised Learning: An In-depth Parameter Analysis Davidson, Padraig; Buckermann, Florian; Steininger, Michael; Krause, Anna; Hotho, Andreas in KI 2021: Advances in Artificial Intelligence, S. Edelkamp, R. M{\"o}ller, E. Rueckert (reds.) (2021). 51–66.
- [ Abstract ]
- [ BibSonomy-Post ]
Creating datasets for supervised learning is a very challenging and expensive task, in which each input example has to be annotated with its expected output (e.g. object class). By combining unsupervised and semi-supervised learning, semi-unsupervised learning proposes a new paradigm for partially labeled datasets with additional unknown classes. In this paper we focus on a better understanding of this new learning paradigm and analyze the impact of the amount of labeled data, the number of augmented classes and the selection of hidden classes on the quality of prediction. Especially the number of augmented classes highly influences classification accuracy, which needs tuning for each dataset, since too few and too many augmented classes are detrimental to classifier performance. We also show that we can improve results on a large variety of datasets when using convolutional networks as feature extractors while applying output driven entropy regularization instead of a simple weight based L2 norm.
Automating the optical identification of abrasive wear on electrical contact pins Buckermann, Florian; Klement, Nils; Beyer, Oliver; Hütten, Andreas; Hammer, Barbara in at - Automatisierungstechnik (2021). 69(10) 903–914.
- [ Abstract ]
- [ DOI ]
- [ BibSonomy-Post ]
The automation of quality control in manufacturing has made great strides in recent years, in particular following new developments in machine learning, specifically deep learning, which allow to solve challenging tasks such as visual inspection or quality prediction. Yet, optimum quality control pipelines are often not obvious in specific settings, since they do not necessarily align with (supervised) machine learning tasks. In this contribution, we introduce a new automation pipeline for the quantification of wear on electrical contact pins. More specifically, we propose and test a novel pipeline which combines a deep network for image segmentation with geometric priors of the problem. This task is important for a judgement of the quality of the material and it can serve as a starting point to optimize the choices of materials based on its automated evaluation.

Projects and Research Interests

Teaching

Publications

Data privacy protection

Data privacy protection

Picture credits