activity
20222025
most citedFeasibility of Inconspicuous GAN-generated Adversarial Patches against Object Detection

6 citations · 15 across the 23 of their papers we have counts for

collaborators

23 papers

cs.CV2025

Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers

Svetlana Pavlitska, Haixi Fan, Konstantin Ditschuneit +1

Robustifying convolutional neural networks (CNNs) against adversarial attacks remains challenging and often requires resource-intensive countermeasures. We explore the use of spars…

cs.CV2025

Extracting Uncertainty Estimates from Mixtures of Experts for Semantic Segmentation

Svetlana Pavlitska, Beyza Keskin, Alwin Faßbender +2

Estimating accurate and well-calibrated predictive uncertainty is important for enhancing the reliability of computer vision models, especially in safety-critical applications like…

cs.CV2025

EffiComm: Bandwidth Efficient Multi Agent Communication

Melih Yazgan, Allen Xavier Arasan, J. Marius Zöllner

Collaborative perception allows connected vehicles to exchange sensor information and overcome each vehicle's blind spots. Yet transmitting raw point clouds or full feature maps ov…

cs.LG2025

Goal-based Trajectory Prediction for improved Cross-Dataset Generalization

Daniel Grimm, Ahmed Abouelazm, J. Marius Zöllner

To achieve full autonomous driving, a good understanding of the surrounding environment is necessary. Especially predicting the future states of other traffic participants imposes…

cs.RO2025

Functionality Assessment Framework for Autonomous Driving Systems using Subjective Networks

Stefan Orf, Sven Ochs, Valentin Marotta +3

In complex autonomous driving (AD) software systems, the functioning of each system part is crucial for safe operation. By measuring the current functionality or operability of ind…

cs.CV2025

Contrast & Compress: Learning Lightweight Embeddings for Short Trajectories

Abhishek Vivekanandan, Christian Hubschneider, J. Marius Zöllner

The ability to retrieve semantically and directionally similar short-range trajectories with both accuracy and efficiency is foundational for downstream applications such as motion…