6 papers
Train, Test, Re-evaluate: Schedule-Sensitive Evaluation of Generative Data for Hand Detection
Atmika Bhardwaj, Silvia Vock, Nico Steckhan
Generated (or synthetic) image data is increasingly used to augment or replace real training datasets when target imagery is scarce, expensive, or biased. For hand detection, parti…
Semantic Robustness Probing via Inpainting: An Interactive Tool for Safety-Critical Object Detection
Nico Steckhan, Krutarth Prajapati, Weija Shao +1
Testing object detectors in safety-critical domains requires semantically meaningful probes beyond pixel-level corruptions. We present SemProbe, a tool for semantic robustness prob…
Utilizing Class Separation Distance for the Evaluation of Corruption Robustness of Machine Learning Classifiers
Georg Siedel, Silvia Vock, Andrey Morozov +1
Robustness is a fundamental pillar of Machine Learning (ML) classifiers, substantially determining their reliability. Methods for assessing classifier robustness are therefore esse…
Stylized Synthetic Augmentation further improves Corruption Robustness
Georg Siedel, Rojan Regmi, Abhirami Anand +3
This paper proposes a training data augmentation pipeline that combines synthetic image data with neural style transfer in order to address the vulnerability of deep vision models…
Combined Image Data Augmentations diminish the benefits of Adaptive Label Smoothing
Georg Siedel, Ekagra Gupta, Weijia Shao +2
Soft augmentation regularizes the supervised learning process of image classifiers by reducing label confidence of a training sample based on the magnitude of random-crop augmentat…
Dynamic Risk Assessment for Human-Robot Collaboration Using a Heuristics-based Approach
Georgios Katranis, Frederik Plahl, Joachim Grimstadt +3
Human-robot collaboration (HRC) introduces significant safety challenges, particularly in protecting human operators working alongside collaborative robots (cobots). While current…