Deep neural networks (DNN) have made impressive progress in the
interpre...
Uncertainty estimation bears the potential to make deep learning (DL) sy...
Many machine learning applications can benefit from simulated data for
s...
Enabling autonomous driving (AD) can be considered one of the biggest
ch...
Statistical models are inherently uncertain. Quantifying or at least
upp...
Instance segmentation with neural networks is an essential task in
envir...
Despite recent advancements, deep neural networks are not robust against...
Deep neural networks are often not robust to semantically-irrelevant cha...
In this paper we propose a framework for assessing the risk associated w...
Autonomous driving requires self awareness of its perception functions.
...
Safety is one of the most important development goals for highly automat...
In semantic segmentation datasets, classes of high importance are oftent...
In recent years, deep learning methods have outperformed other methods i...
Neural networks for semantic segmentation can be seen as statistical mod...
Most state-of-the-art machine learning (ML) classification systems are
v...
The high amount of sensors required for autonomous driving poses enormou...
As part of autonomous car driving systems, semantic segmentation is an
e...
We present a method that "meta" classifies whether segments (objects)
pr...
It has been shown that injecting noise into the neural network weights d...
We propose an efficient protocol for decentralized training of deep neur...