6 papers
From Model Uncertainty to Human Attention: Localization-Aware Visual Cues for Scalable Annotation Review
Moussa Kassem Sbeyti, Joshua Holstein, Philipp Spitzer +2
High-quality labeled data is essential for training robust machine learning models, yet obtaining annotations at scale remains expensive. AI-assisted annotation has therefore becom…
Probabilistic Object Detection with Conformal Prediction
Christopher Ries, Moussa Kassem Sbeyti, Nicolas Bianco +1
Conformal Prediction (CP) is a distribution-free method for constructing prediction sets with marginal finite-sample coverage guarantees, making it a suitable framework for reliabl…
Depth as Prior Knowledge for Object Detection
Moussa Kassem Sbeyti, Nadja Klein
Detecting small and distant objects remains challenging for object detectors due to scale variation, low resolution, and background clutter. Safety-critical applications require re…
Streamlining the Development of Active Learning Methods in Real-World Object Detection
Moussa Kassem Sbeyti, Nadja Klein, Michelle Karg +2
Active learning (AL) for real-world object detection faces computational and reliability challenges that limit practical deployment. Developing new AL methods requires training mul…
Prediction Accuracy & Reliability: Classification and Object Localization under Distribution Shift
Fabian Diet, Moussa Kassem Sbeyti, Michelle Karg
Natural distribution shift causes a deterioration in the perception performance of convolutional neural networks (CNNs). This comprehensive analysis for real-world traffic data add…
Cost-Sensitive Uncertainty-Based Failure Recognition for Object Detection
Moussa Kassem Sbeyti, Michelle Karg, Christian Wirth +2
Object detectors in real-world applications often fail to detect objects due to varying factors such as weather conditions and noisy input. Therefore, a process that mitigates fals…