8 citations · 23 across the 27 of their papers we have counts for
29 papers
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…
RoG-DAgger: Rollout-Guided Post-Training for End-to-End Driving
Liangyu Zhong, Joachim Sicking, Fabian Hueger +1
Recent end-to-end driving systems demonstrate strong performance on closed-loop benchmarks, yet are still predominantly trained on fixed expert-collected data using open-loop imita…
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…
Generative Design of a Gas Turbine Combustor Using Invertible Neural Networks
Patrick Krüger, Hanno Gottschalk, Werner Krebs +1
The need to burn 100% H2 in high efficient gas turbines featuring low NOx combustion in premix mode require the complete redesign of the combustion system to ensure stable operatio…
How well do generative models solve inverse problems? A benchmark study
Patrick Krüger, Patrick Materne, Werner Krebs +1
Generative learning generates high dimensional data based on low dimensional conditions, also called prompts. Therefore, generative learning algorithms are eligible for solving (Ba…
Generative Design of Ship Propellers using Conditional Flow Matching
Patrick Kruger, Rafael Diaz, Simon Hauschulz +2
In this paper, we explore the use of generative artificial intelligence (GenAI) for ship propeller design. While traditional forward machine learning models predict the performance…
Domain Generalization for Semantic Segmentation: A Survey
Manuel Schwonberg, Hanno Gottschalk
The generalization of deep neural networks to unknown domains is a major challenge despite their tremendous progress in recent years. For this reason, the dynamic area of domain ge…
Decomposing and Revising What Language Models Generate
Zhichao Yan, Jiaoyan Chen, Jiapu Wang +3
Attribution is crucial in question answering (QA) with Large Language Models (LLMs).SOTA question decomposition-based approaches use long form answers to generate questions for ret…
When do World Models Successfully Learn Dynamical Systems?
Edmund Ross, Claudia Drygala, Leonhard Schwarz +4
In this work, we explore the use of compact latent representations with learned time dynamics ('World Models') to simulate physical systems. Drawing on concepts from control theory…
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…
Learning to Integrate
Oliver G. Ernst, Hanno Gottschalk, Toni Kowalewitz +1
We address uncertainty quantification for a generic input distribution to some resource-intensive simulation, e.g., requiring the solution of a partial differential equation. While…
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…
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…
Generative AI for Autonomous Driving: A Review
Katharina Winter, Abhishek Vivekanandan, Rupert Polley +17
Generative AI (GenAI) is rapidly advancing the field of Autonomous Driving (AD), extending beyond traditional applications in text, image, and video generation. We explore how gene…
Learning Brenier Potentials with Convex Generative Adversarial Neural Networks
Claudia Drygala, Hanno Gottschalk, Thomas Kruse +2
Brenier proved that under certain conditions on a source and a target probability measure there exists a strictly convex function such that its gradient is a transport map from the…
Efficient Contrastive Decoding with Probabilistic Hallucination Detection - Mitigating Hallucinations in Large Vision Language Models -
Laura Fieback, Nishilkumar Balar, Jakob Spiegelberg +1
Despite recent advances in Large Vision Language Models (LVLMs), these models still suffer from generating hallucinatory responses that do not align with the visual input provided.…
Out-of-Distribution Segmentation in Autonomous Driving: Problems and State of the Art
Youssef Shoeb, Azarm Nowzad, Hanno Gottschalk
In this paper, we review the state of the art in Out-of-Distribution (OoD) segmentation, with a focus on road obstacle detection in automated driving as a real-world application. W…
Adaptive Neural Networks for Intelligent Data-Driven Development
Youssef Shoeb, Azarm Nowzad, Hanno Gottschalk
Advances in machine learning methods for computer vision tasks have led to their consideration for safety-critical applications like autonomous driving. However, effectively integr…
Segment-Level Road Obstacle Detection Using Visual Foundation Model Priors and Likelihood Ratios
Youssef Shoeb, Nazir Nayal, Azarm Nowzad +2
Detecting road obstacles is essential for autonomous vehicles to navigate dynamic and complex traffic environments safely. Current road obstacle detection methods typically assign…
A Study on Unsupervised Domain Adaptation for Semantic Segmentation in the Era of Vision-Language Models
Manuel Schwonberg, Claus Werner, Hanno Gottschalk +1
Despite the recent progress in deep learning based computer vision, domain shifts are still one of the major challenges. Semantic segmentation for autonomous driving faces a wide r…
Comparison of Generative Learning Methods for Turbulence Surrogates
Claudia Drygala, Edmund Ross, Mohammad Sharifi Ghazijahani +3
Numerical simulations of turbulent flows present significant challenges in fluid dynamics due to their complexity and high computational cost. High resolution techniques such as Di…
New advances in universal approximation with neural networks of minimal width
Dennis Rochau, Robin Chan, Hanno Gottschalk
We prove several universal approximation results at minimal or near-minimal width for approximation of and $C^0(\mathbb{R}^{d_x}, \mathbb{…
On the Influence of Shape, Texture and Color for Learning Semantic Segmentation
Annika Mütze, Natalie Grabowsky, Edgar Heinert +2
Recent research has investigated the shape and texture biases of pre-trained deep neural networks (DNNs) in image classification. Those works test how much a trained DNN relies on…
VL4AD: Vision-Language Models Improve Pixel-wise Anomaly Detection
Liangyu Zhong, Joachim Sicking, Fabian Hüger +1
Semantic segmentation networks have achieved significant success under the assumption of independent and identically distributed data. However, these networks often struggle to det…