Philipp Oberdiek
PhD Candidate, Researcher, Coffee Enthusiast
Publications
May 2022
UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANs
Philipp Oberdiek, Gernot A. Fink, Matthias Rottmann
Preprint. Under review.
June 2020
Detection and Retrieval of Out-of-Distribution Objects in Semantic Segmentation
Philipp Oberdiek, Matthias Rottmann, Gernot A. Fink
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Seattle, USA, 2020
September 2019
Exploring Confidence Measures for Word Spotting in Heterogeneous Datasets
Fabian Wolf, Philipp Oberdiek, Gernot A. Fink
Proc. Int. Conf. on Document Analysis and Recognition, Sydney, Australia, 2019
September 2018
Classification Uncertainty of Deep Neural Networks Based on Gradient Information
Philipp Oberdiek, Matthias Rottmann, Hanno Gottschalk
8th IAPR TC 3 Workshop on Artificial Neural Networks for Pattern Recognition, Siena, Italy, 2018
Education
Since April 2018
PhD – Computer Science
Pattern Recognition in Embedded Systems Group
Computer Science XII
TU Dortmund University
Dortmund, Germany
April 2018
Barmenia-Math-Award 2017 – First Place
For one of the best graduations of the year
March 2018
Master of Science – Mathematics
University of Wuppertal
Wuppertal, Germany
Grade: 1.1
With First Class Honours
July 2015
Bachelor of Science – Business Mathematics
University of Wuppertal
Wuppertal, Germany
Grade: 2.3
June 2012
A-Level
Röntgengymnasium (Grammar School)
Remscheid, Germany
Work Experience
Since April 2018
Research Assistant
Pattern Recognition in Embedded Systems Group
Computer Science XII
TU Dortmund University
Dortmund, Germany
2013 – 2018
Student Research Assistant
University of Wuppertal
Wuppertal, Germany
2017
Internship – Siemens AG
Mühlheim an der Ruhr, Germany
Division Power and Gas
Responsibilities: Machine Learning and Data Analysis
2014
Internship – Commerz Real AG
Düsseldorf, Germany
Responsibilities: Workflow Automation