161 citations · 338 across the 33 of their papers we have counts for
17 papers · 1 filter
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…
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…
Runtime Safety Monitoring of Deep Neural Networks for Perception: A Survey
Albert Schotschneider, Svetlana Pavlitska, J. Marius Zöllner
Deep neural networks (DNNs) are widely used in perception systems for safety-critical applications, such as autonomous driving and robotics. However, DNNs remain vulnerable to vari…
DEAP DIVE: Dataset Investigation with Vision transformers for EEG evaluation
Annemarie Hoffsommer, Helen Schneider, Svetlana Pavlitska +1
Accurately predicting emotions from brain signals has the potential to achieve goals such as improving mental health, human-computer interaction, and affective computing. Emotion p…
CrowdQuery: Density-Guided Query Module for Enhanced 2D and 3D Detection in Crowded Scenes
Marius Dähling, Sebastian Krebs, J. Marius Zöllner
This paper introduces a novel method for end-to-end crowd detection that leverages object density information to enhance existing transformer-based detectors. We present CrowdQuery…
Towards Adversarial Robustness of Model-Level Mixture-of-Experts Architectures for Semantic Segmentation
Svetlana Pavlitska, Enrico Eisen, J. Marius Zöllner
Vulnerability to adversarial attacks is a well-known deficiency of deep neural networks. Larger networks are generally more robust, and ensembling is one method to increase adversa…
Evaluating Adversarial Attacks on Traffic Sign Classifiers beyond Standard Baselines
Svetlana Pavlitska, Leopold Müller, J. Marius Zöllner
Adversarial attacks on traffic sign classification models were among the first successfully tried in the real world. Since then, the research in this area has been mainly restricte…
TLD-READY: Traffic Light Detection -- Relevance Estimation and Deployment Analysis
Nikolai Polley, Svetlana Pavlitska, Yacin Boualili +4
Effective traffic light detection is a critical component of the perception stack in autonomous vehicles. This work introduces a novel deep-learning detection system while addressi…
Hybrid Video Anomaly Detection for Anomalous Scenarios in Autonomous Driving
Daniel Bogdoll, Jan Imhof, Tim Joseph +2
In autonomous driving, the most challenging scenarios can only be detected within their temporal context. Most video anomaly detection approaches focus either on surveillance or tr…
UMAD: Unsupervised Mask-Level Anomaly Detection for Autonomous Driving
Daniel Bogdoll, Noël Ollick, Tim Joseph +2
Dealing with atypical traffic scenarios remains a challenging task in autonomous driving. However, most anomaly detection approaches cannot be trained on raw sensor data but requir…
AnoVox: A Benchmark for Multimodal Anomaly Detection in Autonomous Driving
Daniel Bogdoll, Iramm Hamdard, Lukas Namgyu Rößler +9
The scale-up of autonomous vehicles depends heavily on their ability to deal with anomalies, such as rare objects on the road. In order to handle such situations, it is necessary t…
CAGE: Circumplex Affect Guided Expression Inference
Niklas Wagner, Felix Mätzler, Samed R. Vossberg +3
Understanding emotions and expressions is a task of interest across multiple disciplines, especially for improving user experiences. Contrary to the common perception, it has been…
Conditioning Latent-Space Clusters for Real-World Anomaly Classification
Daniel Bogdoll, Svetlana Pavlitska, Simon Klaus +1
Anomalies in the domain of autonomous driving are a major hindrance to the large-scale deployment of autonomous vehicles. In this work, we focus on high-resolution camera data from…
Self Supervised Clustering of Traffic Scenes using Graph Representations
Maximilian Zipfl, Moritz Jarosch, J. Marius Zöllner
Examining graphs for similarity is a well-known challenge, but one that is mandatory for grouping graphs together. We present a data-driven method to cluster traffic scenes that is…
Multimodal Detection of Unknown Objects on Roads for Autonomous Driving
Daniel Bogdoll, Enrico Eisen, Maximilian Nitsche +2
Tremendous progress in deep learning over the last years has led towards a future with autonomous vehicles on our roads. Nevertheless, the performance of their perception systems i…
Is Neuron Coverage Needed to Make Person Detection More Robust?
Svetlana Pavlitskaya, Şiyar Yıkmış, J. Marius Zöllner
The growing use of deep neural networks (DNNs) in safety- and security-critical areas like autonomous driving raises the need for their systematic testing. Coverage-guided testing…
Temporal Feature Networks for CNN based Object Detection
Michael Weber, Tassilo Wald, J. Marius Zöllner
For reliable environment perception, the use of temporal information is essential in some situations. Especially for object detection, sometimes a situation can only be understood…