162 citations
- Freie Universität BerlinDE10 papers
- Friedrich-Alexander-Universität Erlangen-NürnbergDE9 papers
- University of Veterinary Medicine ViennaAT9 papers
- Technical University of MunichDE8 papers
- Flensburg University of Applied SciencesDE7 papers
- The Schwarzman Animal Medical CenterUS5 papers
- Medical University of ViennaAT4 papers
- Europa-Universität FlensburgDE3 papers
- IDEXX Laboratories (Germany)DE3 papers
- Michigan State UniversityUS3 papers
- Ross University School of Veterinary MedicineKN3 papers
- Universitätsklinikum ErlangenDE3 papers
5 papers · 1 filter
XEngine: Optimal Tensor Rematerialization for Neural Networks in Heterogeneous Environments
Manuela Schuler, Richard Membarth, Philipp Slusallek
Memory efficiency is crucial in training deep learning networks on resource-restricted devices. During backpropagation, forward tensors are used to calculate gradients. Despite the…
Expert-LaSTS: Expert-Knowledge Guided Latent Space for Traffic Scenarios
Jonas Wurst, Lakshman Balasubramanian, Michael Botsch +1
Clustering traffic scenarios and detecting novel scenario types are required for scenario-based testing of autonomous vehicles. These tasks benefit from either good similarity meas…
Stochastic Market Games
Kyrill Schmid, Lenz Belzner, Robert Müller +2
Some of the most relevant future applications of multi-agent systems like autonomous driving or factories as a service display mixed-motive scenarios, where agents might have confl…
Mitosis domain generalization in histopathology images -- The MIDOG challenge
Marc Aubreville, Nikolas Stathonikos, Christof A. Bertram +32
The density of mitotic figures within tumor tissue is known to be highly correlated with tumor proliferation and thus is an important marker in tumor grading. Recognition of mitoti…
Pan-tumor CAnine cuTaneous Cancer Histology (CATCH) dataset
Frauke Wilm, Marco Fragoso, Christian Marzahl +8
Due to morphological similarities, the differentiation of histologic sections of cutaneous tumors into individual subtypes can be challenging. Recently, deep learning-based approac…