5 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…
Can We Challenge Open-Vocabulary Object Detectors with Generated Content in Street Scenes?
Annika Mütze, Sadia Ilyas, Christian Dörpelkus +1
Open-vocabulary object detectors such as Grounding DINO are trained on vast and diverse data, achieving remarkable performance on challenging datasets. Due to that, it is unclear w…
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…
Does Knowledge About Perceptual Uncertainty Help an Agent in Automated Driving?
Natalie Grabowsky, Annika Mütze, Joshua Wendland +2
Agents in real-world scenarios like automated driving deal with uncertainty in their environment, in particular due to perceptual uncertainty. Although, reinforcement learning is d…