Publications

7
Depth as Prior Knowledge for Object Detection
Moussa Kassem Sbeyti and Nadja Klein
arXiv:2602.05730 GitHub
Teaser
Streamlining the Development of Active Learning Methods in Real-World Object Detection
Moussa Kassem Sbeyti, Nadja Klein, Michelle Karg, Christian Wirth, Sahin Albayrak
arXiv:2508.19906 GitHub
Teaser
Building Blocks for Robust and Effective Semi-Supervised Real-World Object Detection
Moussa Kassem Sbeyti, Nadja Klein, Azarm Nowzad, Fikret Sivrikaya, Sahin Albayrak
arXiv:2503.18903 OpenReview GitHub TMLR KleinLab
Teaser
Cost-Sensitive Uncertainty-Based Failure Recognition for Object Detection
Moussa Kassem Sbeyti, Michelle Karg, Christian Wirth, Nadja Klein, Sahin Albayrak
arXiv:2404.17427 PMLR OpenReview GitHub UAI Poster Slides Talk
Figure 2
Overcoming the Limitations of Localization Uncertainty: Efficient & Exact Non-Linear Post-Processing and Calibration
Moussa Kassem Sbeyti, Michelle Karg, Christian Wirth, Azarm Nowzad, Sahin Albayrak
arXiv:2306.08981 Springer GitHub ECML PKDD Slides Talk
Figure 1
Prediction Accuracy & Reliability: Classification and Object Localization under Distribution Shift
Fabian Diet, Moussa Kassem Sbeyti, Michelle Karg
arXiv:2409.03543 Springer
Figure 1
Building Bridges between Bayesian Statistics and Deep Learning
Nadja Klein and Moussa Kassem Sbeyti
Podcast De Gruyter
Teaser

Patents

9
DE102023201734A1
DE102023201735A1
DE102023207709A1
DE102023203027A1
WO2024200136A1
WO2024200137A1
WO2025031549A1
EP4610888A1
EP4610889A1

More

Podcast Bayesian Learning → PhD Thesis Automated Labeling Pipeline for 2D Object Detection
Pipeline
→