Ensembles of independently trained deep neural networks yield uncertaint...
High-resolution wide-angle fisheye images are becoming more and more
imp...
Existing datasets for autonomous driving (AD) often lack diversity and
l...
Images fed to a deep neural network have in general undergone several
ha...
Research connecting text and images has recently seen several breakthrou...
Motion prediction systems aim to capture the future behavior of traffic
...
Predicting the motion of other road agents enables autonomous vehicles t...
Masked autoencoding has become a successful pre-training paradigm for
Tr...
In this paper, we investigate how field programmable gate arrays can ser...
We explore future object prediction – a challenging problem where all
ob...
Accurate uncertainty estimates are essential for deploying deep object
d...
We analyze the role of rotational equivariance in convolutional neural
n...
We survey the mathematical foundations of geometric deep learning, focus...