Franz Köferl
Franz Köferl, M. Sc.
Department Artificial Intelligence in Biomedical Engineering (AIBE)
Lehrstuhl für Maschinelles Lernen und Datenanalytik
Carl-Thiersch-Straße 2b
91052 Erlangen
- Phone number: +49 9131 85-20284
- Email: franz.koeferl@fau.de
- Website: https://www.mad.tf.fau.de/person/franz-koeferl/
| Since 7/2017 | PhD Candidate
Machine Learning and Data Analytics Lab, |
| 5/2014 – 2/2017 | M.Sc. in Computer Science Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Master Thesis : “Segmentation and Classification of Interlinear and Marginal Glosses using Convolutional Neural Networks“ |
| 7/2016 – 6/2017 | Student/Assistant Researcher at Fraunhofer IIS |
| 5/2011 – 5/2014 |
B.Sc. in Computer Science
Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)
Bachelor Thesis: “Experimentelle Untersuchung des Einflusses von Bound-Handling-Strategien auf die Partikel-Verteilung bei der Partikelschwarmoptimierung.” |
Demonstrator Deep Learning
Machine Learning, especially Deep Learning are complex methods for solving various problems, ranging from detection of persons to predicting the time for maintenance of specific parts of a machine. The methods struggle with intuition, when you can solve or when you can’t apply these methods to solve a specific task. This demo demonstrates the conditions needed for a reliable application of deep learning methods and their respective results. Have look at our poster.
The following videos demonstrate an Object Detector Yolov3 [1] trained on naive data, augmentated and simulated from our demo machine. The used data consists of ca. 40,000 images, each manually labeled.
- Trained without any measure
Trained with patch augmentationTrained with simulated images
[1] Joseph Redmon, Ali Farhadi: YOLOv3: An Incremental Improvement.
2023
- Altstidl TR., Nguyen A., Schwinn L., Köferl F., Mutschler C., Eskofier B., Zanca D.:
Just a Matter of Scale? Reevaluating Scale Equivariance in Convolutional Neural Networks
2023 International Joint Conference on Neural Networks (IJCNN) (Gold Coast, Australia, 18. June 2023 - 23. June 2023)
In: Proc. Intl. Joint Conf. Neural Netw. (IJCNN) 2023
DOI: 10.1109/IJCNN54540.2023.10191724
BibTeX: Download - Köferl F., Jami J., Li J., Zanca D., Eskofier B., Zürl M.:
Tracking the visitor: An optical indoor system for visitor research in museums
In: Sonja Thiel, Johannes C. Bernhardt (ed.): AI in Museums: Reflections, Perspectives and Applications, Transcript-Verlag, 2023, p. 287 - 294 (Edition Museum, Vol.74)
ISBN: 9783839467107
DOI: 10.14361/9783839467107
BibTeX: Download - Zürl M., Dirauf R., Köferl F., Steinlein N., Sueskind J., Zanca D., Brehm I., von Fersen L., Eskofier B.:
PolarBearVidID: A Video-Based Re-Identification Benchmark Dataset for Polar Bears
In: Animals 13 (2023), p. 801
ISSN: 2076-2615
DOI: 10.3390/ani13050801
BibTeX: Download
2020
- Köferl F., Link J., Eskofier B.:
Application of SORT on Multi-Object Tracking and Segmentation
Conference on Computer Vision and Pattern Recognition; 5th BMTT MOTChallenge Workshop: Multi-Object Tracking and Segmentation (Seattle, WA, USA (Virtual), 19. June 2020 - 19. June 2020)
URL: https://motchallenge.net/workshops/bmtt2020/papers/Application_and_Adaptations_of_SORT_on_MOTS20.pdf
BibTeX: Download
(Working Paper) - Rüthlein M., Köferl F., Mehringer W., Eskofier B.:
Interactive Segmentation of RGB-D Indoor Scenes using Deep Learning
International Conference on Machine Learning; 2nd ICML 2020 Workshop on Human in the Loop Learning (Virtual Conference, 18. July 2020 - 18. July 2020)
BibTeX: Download
(Conference report)
2015
- Selgrad K., Lier A., Köferl F., Stamminger M., Lohmann D.:
Lightweight, generative variant exploration for high-performance graphics applications
14th International Conference on Generative Programming: Concepts & Experiences (GPCE) (Pittsburgh, PA, 26. October 2015 - 27. October 2015)
In: ACM Bd. 51, Nr. 3 2015
DOI: 10.1145/2814204.2814220
BibTeX: Download
Partners & Funding Agencies
