10 papers
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…
Out-of-Distribution Object Detection in Street Scenes via Synthetic Outlier Exposure and Transfer Learning
Sadia Ilyas, Annika Mütze, Klaus Friedrichs +2
Out-of-distribution (OOD) object detection is an important yet underexplored task. A reliable object detector should be able to handle OOD objects by localizing and correctly class…
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…
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…
Contrast All the Time: Learning Time Series Representation from Temporal Consistency
Abdul-Kazeem Shamba, Kerstin Bach, Gavin Taylor
Representation learning for time series using contrastive learning has emerged as a critical technique for improving the performance of downstream tasks. To advance this effective…