7 papers · 1 filter
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…
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…