S
Stefanie Röhrl
Publications - 8
Citations - 302
Stefanie Röhrl is an academic researcher. The author has contributed to research in topics: Computer science & Pattern recognition (psychology). The author has an hindex of 1, co-authored 1 publications receiving 282 citations.
Papers
More filters
Journal ArticleDOI
Temozolomide preferentially depletes cancer stem cells in glioblastoma.
Dagmar Beier,Stefanie Röhrl,Deepu R. Pillai,Stefanie Schwarz,Leoni A. Kunz-Schughart,Petra Leukel,Martin Proescholdt,Alexander Brawanski,Ulrich Bogdahn,Ariane Trampe-Kieslich,Bernd Giebel,Jörg Wischhusen,Guido Reifenberger,Peter Hau,Christoph P. Beier +14 more
TL;DR: The data strongly suggest that optimized temozolomide-based chemotherapeutic protocols might substantially improve the elimination of GBM stem cells and consequently prolong the survival of patients.
Book ChapterDOI
Towards Cross Domain Transfer Learning for Underwater Correspondence Search
TL;DR: In this paper , a learned robust feature model, D2Net, is applied to the underwater environment and particularly look into the issue of cross domain transfer learning as a strategy to deal with the lack of annotated underwater training data.
Proceedings ArticleDOI
A Comparison of Uncertainty Quantification Methods for Active Learning in Image Classification
Alice Hein,Stefanie Röhrl,Thea Grobel,M. Lengl,Nawal Hafez,Martin Tobias Knopp,Christian Klenk,Dominik Heim,Oliver Hayden,Klaus Diepold +9 more
TL;DR: Seven different UQ methods on three image classification data sets are compared and it is found that Concrete Dropout, Least Confidence, Smallest Margin, and Entropy sampling consistently outperform Random sampling across data sets, whereas Ensembles, Monte-Carlo Drop out, and Bayes-by-Backprop do not.
Journal ArticleDOI
Outlier Detection using Self-Organizing Maps for Automated Blood Cell Analysis
Stefanie Röhrl,Alice Hein,Dominik Heim,Christian Klenk,M. Lengl,Martin Tobias Knopp,Nawal Hafez,Oliver Hayden,Klaus Diepold +8 more
TL;DR: This work assesses the suitability of Self-Organizing Maps for outlier detection specifically on a medical dataset con-taining quantitative phase images of white blood cells and suggests a combination of self-organizing Maps and feature extraction based on deep learning.