10 citations · 16 across the 9 of their papers we have counts for
3 papers · 1 filter
U-CE: Uncertainty-aware Cross-Entropy for Semantic Segmentation
Steven Landgraf, Markus Hillemann, Kira Wursthorn +1
Deep neural networks have shown exceptional performance in various tasks, but their lack of robustness, reliability, and tendency to be overconfident pose challenges for their depl…
Segmentation of Industrial Burner Flames: A Comparative Study from Traditional Image Processing to Machine and Deep Learning
Steven Landgraf, Markus Hillemann, Moritz Aberle +2
In many industrial processes, such as power generation, chemical production, and waste management, accurately monitoring industrial burner flame characteristics is crucial for safe…
DUDES: Deep Uncertainty Distillation using Ensembles for Semantic Segmentation
Steven Landgraf, Kira Wursthorn, Markus Hillemann +1
Deep neural networks lack interpretability and tend to be overconfident, which poses a serious problem in safety-critical applications like autonomous driving, medical imaging, or…