6 papers
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…
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…
PRIMU: Uncertainty Estimation for Novel Views in Gaussian Splatting from Primitive-Based Representations of Error and Coverage
Thomas Gottwald, Edgar Heinert, Peter Stehr +2
We introduce Primitive-based Representations of Uncertainty (PRIMU), a post-hoc uncertainty estimation (UE) framework for Gaussian Splatting (GS). Reliable UE is essential for depl…
On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNs
Gesina Schwalbe, Georgii Mikriukov, Edgar Heinert +5
The thriving research field of concept-based explainable artificial intelligence (C-XAI) investigates how human-interpretable semantic concepts embed in the latent spaces of deep n…
Shape Bias and Robustness Evaluation via Cue Decomposition for Image Classification and Segmentation
Edgar Heinert, Thomas Gottwald, Annika Mütze +1
Previous works studied how deep neural networks (DNNs) perceive image content in terms of their biases towards different image cues, such as texture and shape. Previous methods to…
Uncertainty and Prediction Quality Estimation for Semantic Segmentation via Graph Neural Networks
Edgar Heinert, Stephan Tilgner, Timo Palm +1
When employing deep neural networks (DNNs) for semantic segmentation in safety-critical applications like automotive perception or medical imaging, it is important to estimate thei…