283 citations
- University of RegensburgDE4 papers
- Friedrich-Alexander-Universität Erlangen-NürnbergDE2 papers
- Max Planck Institute for the Science of LightDE2 papers
- Case Western Reserve UniversityUS1 paper
- DKFZ-ZMBH AllianceDE1 paper
- ETH ZurichCH1 paper
- German Cancer Research CenterDE1 paper
- German Center for Neurodegenerative DiseasesDE1 paper
- Heidelberg UniversityDE1 paper
- IBM Research - AlmadenUS1 paper
- Laboratory of Physical ChemistryCH1 paper
- Max Planck Institute for InformaticsDE1 paper
8 papers
Investigation of inverse design of multilayer thin-films with conditional invertible Neural Networks
Alexander Luce, Ali Mahdavi, Heribert Wankerl +1
The task of designing optical multilayer thin-films regarding a given target is currently solved using gradient-based optimization in conjunction with methods that can introduce ad…
Quantitative probing: Validating causal models using quantitative domain knowledge
Daniel Grünbaum, Maike L. Stern, Elmar W. Lang
We present quantitative probing as a model-agnostic framework for validating causal models in the presence of quantitative domain knowledge. The method is constructed as an analogu…
Parameterized Reinforcement Learning for Optical System Optimization
Heribert Wankerl, Maike L. Stern, Ali Mahdavi +2
Designing a multi-layer optical system with designated optical characteristics is an inverse design problem in which the resulting design is determined by several discrete and cont…
Joint Detection and Tracking in Videos with Identification Features
Bharti Munjal, Abdul Rafey Aftab, Sikandar Amin +3
Recent works have shown that combining object detection and tracking tasks, in the case of video data, results in higher performance for both tasks, but they require a high frame-r…
Monte-Carlo Sampling applied to Multiple Instance Learning for Histological Image Classification
Marc Combalia, Veronica Vilaplana
We propose a patch sampling strategy based on a sequential Monte-Carlo method for high resolution image classification in the context of Multiple Instance Learning. When compared w…
Improved Image Boundaries for Better Video Segmentation
Anna Khoreva, Rodrigo Benenson, Fabio Galasso +2
Graph-based video segmentation methods rely on superpixels as starting point. While most previous work has focused on the construction of the graph edges and weights as well as sol…