21 papers
CIG: Exploration via Conditional Information Gain
Tim Joseph, Marcus Fechner, Philipp Stegmaier +2
Intrinsic rewards for exploration in reinforcement learning condition on different contexts: lifelong rewards score each transition against accumulated experience but ignore within…
Towards a Systematic Risk Assessment of Deep Neural Network Limitations in Autonomous Driving Perception
Svetlana Pavlitska, Christopher Gerking, J. Marius Zöllner
Safety and security are essential for the admission and acceptance of automated and autonomous vehicles. Deep neural networks (DNNs) are widely used for perception and further comp…
Domain-Specialized Object Detection via Model-Level Mixtures of Experts
Svetlana Pavlitska, Malte Stüven, Beyza Keskin +1
Mixture-of-Experts (MoE) models provide a structured approach to combining specialized neural networks and offer greater interpretability than conventional ensembles. While MoEs ha…
Design and Behavior of Sparse Mixture-of-Experts Layers in CNN-based Semantic Segmentation
Svetlana Pavlitska, Haixi Fan, Konstantin Ditschuneit +1
Sparse mixture-of-experts (MoE) layers have been shown to substantially increase model capacity without a proportional increase in computational cost and are widely used in transfo…
DenseBEV: Transforming BEV Grid Cells into 3D Objects
Marius Dähling, Sebastian Krebs, J. Marius Zöllner
In current research, Bird's-Eye-View (BEV)-based transformers are increasingly utilized for multi-camera 3D object detection. Traditional models often employ random queries as anch…
Anomaly Detection in Autonomous Driving: A Survey
Daniel Bogdoll, Maximilian Nitsche, J. Marius Zöllner
Nowadays, there are outstanding strides towards a future with autonomous vehicles on our roads. While the perception of autonomous vehicles performs well under closed-set condition…