no code implementations • 27 May 2024 • Steven Landgraf, Markus Hillemann, Theodor Kapler, Markus Ulrich
While a number of promising uncertainty quantification methods have been proposed to address the prevailing shortcomings of deep neural networks like overconfidence and lack of explainability, quantifying predictive uncertainties in the context of joint semantic segmentation and monocular depth estimation has not been explored yet.
no code implementations • 16 Feb 2024 • Steven Landgraf, Markus Hillemann, Theodor Kapler, Markus Ulrich
By implicitly leveraging the predictive uncertainties of the teacher, EMUFormer achieves new state-of-the-art results on Cityscapes and NYUv2 and additionally estimates high-quality predictive uncertainties for both tasks that are comparable or superior to a Deep Ensemble despite being an order of magnitude more efficient.
no code implementations • 22 Dec 2023 • Miriam Jäger, Steven Landgraf, Boris Jutzi
We demonstrate that data constraints such as low-quality images and poses lead to a degradation of the training process, increased density uncertainty and decreased predicted density.
no code implementations • 19 Jul 2023 • Steven Landgraf, Markus Hillemann, Kira Wursthorn, Markus Ulrich
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 deployment in safety-critical applications like autonomous driving.
no code implementations • 26 Jun 2023 • Steven Landgraf, Markus Hillemann, Moritz Aberle, Valentin Jung, Markus Ulrich
In many industrial processes, such as power generation, chemical production, and waste management, accurately monitoring industrial burner flame characteristics is crucial for safe and efficient operation.
no code implementations • 17 Mar 2023 • Steven Landgraf, Kira Wursthorn, Markus Hillemann, Markus Ulrich
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 machine vision tasks with high demands on reliability.