38 citations · 94 across the 18 of their papers we have counts for
21 papers
Combining Foundation Model Confidence and Monocular Depth for Training-Free Out-of-Distribution Segmentation
Serin Varghese, Fabian Hüger, Kira Maag
Autonomous vehicles operating in open-world scenarios are inevitably confronted with previously unknown objects, such as exotic animals or loose cargo. The reliable detection and s…
Diffuse2Seg: Diffusion Models Can Segment Anything Without Supervision
Christoph Hümmer, Joachim Sicking, Fabian Hüger +1
Open-world entity segmentation aims to predict masks for arbitrary objects across domains and at multiple granularities, from parts to whole objects. In this setting, SAM sets a st…
Do Not Forget the Obvious - RISC: A Risk-Informed Slice-Coverage Protocol for Safe Autonomous Driving
Fabian Hüger
Aggregate metrics may not fully reflect performance in insufficiently examined high-risk driving conditions. We propose RISC (Risk-Informed Slice Coverage), a practical protocol fo…
FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering
Liangyu Zhong, Fabio Rosenthal, Joachim Sicking +4
While Multimodal Large Language Models (MLLMs) offer strong perception and reasoning capabilities for image-text input, Visual Question Answering (VQA) focusing on small image deta…
What should AI see? Using the Public's Opinion to Determine the Perception of an AI
Robin Chan, Radin Dardashti, Meike Osinski +7
Deep neural networks (DNN) have made impressive progress in the interpretation of image data, so that it is conceivable and to some degree realistic to use them in safety critical…
Validation of Simulation-Based Testing: Bypassing Domain Shift with Label-to-Image Synthesis
Julia Rosenzweig, Eduardo Brito, Hans-Ulrich Kobialka +8
Many machine learning applications can benefit from simulated data for systematic validation - in particular if real-life data is difficult to obtain or annotate. However, since si…
Approaching Neural Network Uncertainty Realism
Joachim Sicking, Alexander Kister, Matthias Fahrland +5
Statistical models are inherently uncertain. Quantifying or at least upper-bounding their uncertainties is vital for safety-critical systems such as autonomous vehicles. While stan…
A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs
Nikhil Kapoor, Chun Yuan, Jonas Löhdefink +6
Deep neural networks are often not robust to semantically-irrelevant changes in the input. In this work we address the issue of robustness of state-of-the-art deep convolutional ne…
Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates
Kira Maag, Matthias Rottmann, Serin Varghese +3
Instance segmentation with neural networks is an essential task in environment perception. In many works, it has been observed that neural networks can predict false positive insta…
From a Fourier-Domain Perspective on Adversarial Examples to a Wiener Filter Defense for Semantic Segmentation
Nikhil Kapoor, Andreas Bär, Serin Varghese +4
Despite recent advancements, deep neural networks are not robust against adversarial perturbations. Many of the proposed adversarial defense approaches use computationally expensiv…
Risk Assessment for Machine Learning Models
Paul Schwerdtner, Florens Greßner, Nikhil Kapoor +5
In this paper we propose a framework for assessing the risk associated with deploying a machine learning model in a specified environment. For that we carry over the risk definitio…
Self-Supervised Domain Mismatch Estimation for Autonomous Perception
Jonas Löhdefink, Justin Fehrling, Marvin Klingner +4
Autonomous driving requires self awareness of its perception functions. Technically spoken, this can be realized by observers, which monitor the performance indicators of various p…
Strategy to Increase the Safety of a DNN-based Perception for HAD Systems
Timo Sämann, Peter Schlicht, Fabian Hüger
Safety is one of the most important development goals for highly automated driving (HAD) systems. This applies in particular to the perception function driven by Deep Neural Networ…
MetaFusion: Controlled False-Negative Reduction of Minority Classes in Semantic Segmentation
Robin Chan, Matthias Rottmann, Fabian Hüger +2
In semantic segmentation datasets, classes of high importance are oftentimes underrepresented, e.g., humans in street scenes. Neural networks are usually trained to reduce the over…
Detection of False Positive and False Negative Samples in Semantic Segmentation
Matthias Rottmann, Kira Maag, Robin Chan +3
In recent years, deep learning methods have outperformed other methods in image recognition. This has fostered imagination of potential application of deep learning technology incl…
The Ethical Dilemma when (not) Setting up Cost-based Decision Rules in Semantic Segmentation
Robin Chan, Matthias Rottmann, Radin Dardashti +3
Neural networks for semantic segmentation can be seen as statistical models that provide for each pixel of one image a probability distribution on predefined classes. The predicted…
The Attack Generator: A Systematic Approach Towards Constructing Adversarial Attacks
Felix Assion, Peter Schlicht, Florens Greßner +4
Most state-of-the-art machine learning (ML) classification systems are vulnerable to adversarial perturbations. As a consequence, adversarial robustness poses a significant challen…
GAN- vs. JPEG2000 Image Compression for Distributed Automotive Perception: Higher Peak SNR Does Not Mean Better Semantic Segmentation
Jonas Löhdefink, Andreas Bär, Nico M. Schmidt +3
The high amount of sensors required for autonomous driving poses enormous challenges on the capacity of automotive bus systems. There is a need to understand tradeoffs between bitr…
Application of Decision Rules for Handling Class Imbalance in Semantic Segmentation
Robin Chan, Matthias Rottmann, Fabian Hüger +2
As part of autonomous car driving systems, semantic segmentation is an essential component to obtain a full understanding of the car's environment. One difficulty, that occurs whil…
Prediction Error Meta Classification in Semantic Segmentation: Detection via Aggregated Dispersion Measures of Softmax Probabilities
Matthias Rottmann, Pascal Colling, Thomas-Paul Hack +4
We present a method that "meta" classifies whether seg-ments predicted by a semantic segmentation neural networkintersect with the ground truth. For this purpose, we employ measure…
Efficient Decentralized Deep Learning by Dynamic Model Averaging
Michael Kamp, Linara Adilova, Joachim Sicking +4
We propose an efficient protocol for decentralized training of deep neural networks from distributed data sources. The proposed protocol allows to handle different phases of model…