U
Ullrich Köthe
Researcher at Heidelberg University
Publications - 126
Citations - 3888
Ullrich Köthe is an academic researcher from Heidelberg University. The author has contributed to research in topics: Computer science & Image segmentation. The author has an hindex of 25, co-authored 112 publications receiving 3045 citations. Previous affiliations of Ullrich Köthe include Interdisciplinary Center for Scientific Computing & Fundamental Research on Matter Institute for Atomic and Molecular Physics.
Papers
More filters
Proceedings ArticleDOI
Ilastik: Interactive learning and segmentation toolkit
TL;DR: Ilastik as mentioned in this paper is an easy-to-use tool which allows the user without expertise in image processing to perform segmentation and classification in a unified way, based on labels provided by the user through a convenient mouse interface.
Posted Content
Guided Image Generation with Conditional Invertible Neural Networks
TL;DR: This work introduces a new architecture called conditional invertible neural network (cINN), which combines the purely generative INN model with an unconstrained feed-forward network, which efficiently preprocesses the conditioning input into useful features.
Proceedings Article
Analyzing Inverse Problems with Invertible Neural Networks
Lynton Ardizzone,Jakob Kruse,Sebastian J. Wirkert,Daniel Rahner,Eric W. Pellegrini,Ralf S. Klessen,Lena Maier-Hein,Carsten Rother,Ullrich Köthe +8 more
TL;DR: In this paper, the inverse distribution of hidden system parameters is learned jointly with the well-defined forward process using additional latent output variables to capture the information otherwise lost, which is called Invertible Neural Networks (INNs).
Posted Content
Analyzing Inverse Problems with Invertible Neural Networks
Lynton Ardizzone,Jakob Kruse,Sebastian J. Wirkert,Daniel Rahner,Eric W. Pellegrini,Ralf S. Klessen,Lena Maier-Hein,Carsten Rother,Ullrich Köthe +8 more
TL;DR: It is argued that a particular class of neural networks is well suited for this task -- so-called Invertible Neural Networks (INNs), and it is verified experimentally that INNs are a powerful analysis tool to find multi-modalities in parameter space, to uncover parameter correlations, and to identify unrecoverable parameters.
Book ChapterDOI
Edge and Junction Detection with an Improved Structure Tensor
TL;DR: In this paper, three modifications to the structure tensor approach to low-level feature extraction are described. But they do not address the problem of low-resolution feature extraction, and they only consider edge and junction information.