70 citations · 138 across the 14 of their papers we have counts for
17 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…
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…
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…
Guideline for Trustworthy Artificial Intelligence -- AI Assessment Catalog
Maximilian Poretschkin, Anna Schmitz, Maram Akila +11
Artificial Intelligence (AI) has made impressive progress in recent years and represents a key technology that has a crucial impact on the economy and society. However, it is clear…
A Survey on Uncertainty Toolkits for Deep Learning
Maximilian Pintz, Joachim Sicking, Maximilian Poretschkin +1
The success of deep learning (DL) fostered the creation of unifying frameworks such as tensorflow or pytorch as much as it was driven by their creation in return. Having common bui…
Tailored Uncertainty Estimation for Deep Learning Systems
Joachim Sicking, Maram Akila, Jan David Schneider +4
Uncertainty estimation bears the potential to make deep learning (DL) systems more reliable. Standard techniques for uncertainty estimation, however, come along with specific combi…
Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
Sebastian Houben, Stephanie Abrecht, Maram Akila +38
The use of deep neural networks (DNNs) in safety-critical applications like mobile health and autonomous driving is challenging due to numerous model-inherent shortcomings. These s…
Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilities
Julia Rosenzweig, Joachim Sicking, Sebastian Houben +2
An important pillar for safe machine learning (ML) is the systematic mitigation of weaknesses in neural networks to afford their deployment in critical applications. An ubiquitous…
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 Novel Regression Loss for Non-Parametric Uncertainty Optimization
Joachim Sicking, Maram Akila, Maximilian Pintz +3
Quantification of uncertainty is one of the most promising approaches to establish safe machine learning. Despite its importance, it is far from being generally solved, especially…
DenseHMM: Learning Hidden Markov Models by Learning Dense Representations
Joachim Sicking, Maximilian Pintz, Maram Akila +1
We propose DenseHMM - a modification of Hidden Markov Models (HMMs) that allows to learn dense representations of both the hidden states and the observables. Compared to the standa…
Wasserstein Dropout
Joachim Sicking, Maram Akila, Maximilian Pintz +3
Despite of its importance for safe machine learning, uncertainty quantification for neural networks is far from being solved. State-of-the-art approaches to estimate neural uncerta…
Characteristics of Monte Carlo Dropout in Wide Neural Networks
Joachim Sicking, Maram Akila, Tim Wirtz +2
Monte Carlo (MC) dropout is one of the state-of-the-art approaches for uncertainty estimation in neural networks (NNs). It has been interpreted as approximately performing Bayesian…
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…
Concurrent Credit Portfolio Losses
Joachim Sicking, Thomas Guhr, Rudi Schäfer
We consider the problem of concurrent portfolio losses in two non-overlapping credit portfolios. In order to explore the full statistical dependence structure of such portfolio los…
Pulse shape dependence in the dynamically assisted Sauter-Schwinger effect
Malte F. Linder, Christian Schneider, Joachim Sicking +2
While the Sauter-Schwinger effect describes nonperturbative electron-positron pair creation from vacuum by a strong and slowly varying electric field via tunn…