29 citations · 86 across the 22 of their papers we have counts for
24 papers
A Probabilistic Perspective on Wasserstein-Based Evidential Uncertainty for Out-of-Distribution Segmentation
Arnold Brosch, Abdelrahman Eldesokey, Michael Felsberg +1
Semantic segmentation networks operate on a fixed set of classes and therefore fail when out-of-distribution (OOD) objects appear during deployment, a critical limitation for safet…
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…
Extended Field of View Analysis for VideoGAN-based Trajectory Generation
Annajoyce Mariani, Kira Maag, Hanno Gottschalk
Realistic and diverse trajectory generation is central to enabling higher levels of vehicle automation. While rule-based and classical learning-based methods may struggle to captur…
Texture-Shape Bias Balancing for Robust Synthetic-to-Real Semantic Segmentation in Automotive NIR Imagery
Felix Stillger, Ben Hamscher, Lukas Hahn +3
Semantic segmentation is a fundamental component of visual perception in modern automotive systems, enabling pixel-level scene understanding. Near-Infrared imaging (NIR) offers sta…
Spatio-Temporal Attention for Consistent Video Semantic Segmentation in Automated Driving
Serin Varghese, Kevin Ross, Fabian Hueger +1
Deep neural networks, especially transformer-based architectures, have achieved remarkable success in semantic segmentation for environmental perception. However, existing models p…
Out-of-Distribution Segmentation via Wasserstein-Based Evidential Uncertainty
Arnold Brosch, Abdelrahman Eldesokey, Michael Felsberg +1
Deep neural networks achieve superior performance in semantic segmentation, but are limited to a predefined set of classes, which leads to failures when they encounter unknown obje…
Dance Style Classification using Laban-Inspired and Frequency-Domain Motion Features
Ben Hamscher, Arnold Brosch, Nicolas Binninger +2
Dance is an essential component of human culture and serves as a tool for conveying emotions and telling stories. Identifying and distinguishing dance genres based on motion data i…
Transferring Styles for Reduced Texture Bias and Improved Robustness in Semantic Segmentation Networks
Ben Hamscher, Edgar Heinert, Annika Mütze +2
Recent research has investigated the shape and texture biases of deep neural networks (DNNs) in image classification which influence their generalization capabilities and robustnes…
VideoGAN-based Trajectory Proposal for Automated Vehicles
Annajoyce Mariani, Kira Maag, Hanno Gottschalk
Being able to generate realistic trajectory options is at the core of increasing the degree of automation of road vehicles. While model-driven, rule-based, and classical learning-b…
Towards Reliable Detection of Empty Space: Conditional Marked Point Processes for Object Detection
Tobias J. Riedlinger, Kira Maag, Hanno Gottschalk
Deep neural networks have set the state-of-the-art in computer vision tasks such as bounding box detection and semantic segmentation. Object detectors and segmentation models assig…
Multi-Scale Foreground-Background Confidence for Out-of-Distribution Segmentation
Samuel Marschall, Kira Maag
Deep neural networks have shown outstanding performance in computer vision tasks such as semantic segmentation and have defined the state-of-the-art. However, these segmentation mo…
Integrating uncertainty quantification into randomized smoothing based robustness guarantees
Sina Däubener, Kira Maag, David Krueger +1
Deep neural networks have proven to be extremely powerful, however, they are also vulnerable to adversarial attacks which can cause hazardous incorrect predictions in safety-critic…
Detecting Adversarial Attacks in Semantic Segmentation via Uncertainty Estimation: A Deep Analysis
Kira Maag, Roman Resner, Asja Fischer
Deep neural networks have demonstrated remarkable effectiveness across a wide range of tasks such as semantic segmentation. Nevertheless, these networks are vulnerable to adversari…
Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion
Edgar Heinert, Matthias Rottmann, Kira Maag +1
Convolutional neural networks (CNNs) for image processing tend to focus on localized texture patterns, commonly referred to as texture bias. While most of the previous works in the…
Uncertainty-weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentation
Kira Maag, Asja Fischer
State-of-the-art deep neural networks have been shown to be extremely powerful in a variety of perceptual tasks like semantic segmentation. However, these networks are vulnerable t…
Uncertainty-based Detection of Adversarial Attacks in Semantic Segmentation
Kira Maag, Asja Fischer
State-of-the-art deep neural networks have proven to be highly powerful in a broad range of tasks, including semantic image segmentation. However, these networks are vulnerable aga…
Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentation
Kira Maag, Tobias Riedlinger
In recent years, deep neural networks have defined the state-of-the-art in semantic segmentation where their predictions are constrained to a predefined set of semantic classes. Th…
Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects
Kira Maag, Robin Chan, Svenja Uhlemeyer +2
In this work we present two video test data sets for the novel computer vision (CV) task of out of distribution tracking (OOD tracking). Here, OOD objects are understood as objects…
False Negative Reduction in Semantic Segmentation under Domain Shift using Depth Estimation
Kira Maag, Matthias Rottmann
State-of-the-art deep neural networks demonstrate outstanding performance in semantic segmentation. However, their performance is tied to the domain represented by the training dat…
False Negative Reduction in Video Instance Segmentation using Uncertainty Estimates
Kira Maag
Instance segmentation of images is an important tool for automated scene understanding. Neural networks are usually trained to optimize their overall performance in terms of accura…
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…
Detection of Iterative Adversarial Attacks via Counter Attack
Matthias Rottmann, Kira Maag, Mathis Peyron +2
Deep neural networks (DNNs) have proven to be powerful tools for processing unstructured data. However for high-dimensional data, like images, they are inherently vulnerable to adv…
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…
Time-Dynamic Estimates of the Reliability of Deep Semantic Segmentation Networks
Kira Maag, Matthias Rottmann, Hanno Gottschalk
In the semantic segmentation of street scenes with neural networks, the reliability of predictions is of highest interest. The assessment of neural networks by means of uncertainti…