activity
20242026
collaborators

6 papers

cs.HC2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2025

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…

cs.CV2024

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…

cs.CV2024

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…