Publications

Depth as Prior Knowledge for Object Detection

Moussa Kassem Sbeyti and Nadja Klein

arXiv GitHub

Streamlining the Development of Active Learning Methods in Real-World Object Detection

Moussa Kassem Sbeyti, Nadja Klein, Michelle Karg, Christian Wirth, Sahin Albayrak

arXiv GitHub

Building Blocks for Robust and Effective Semi-Supervised Real-World Object Detection

Moussa Kassem Sbeyti, Nadja Klein, Azarm Nowzad, Fikret Sivrikaya, Sahin Albayrak

arXiv OR GitHub TMLR Kleinlab

Cost-Sensitive Uncertainty-Based Failure Recognition for Object Detection

Moussa Kassem Sbeyti, Michelle Karg, Christian Wirth, Nadja Klein, Sahin Albayrak

arXiv PMLR OR GitHub UAI UAI Poster UAI Pres slides UAI Pres

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 Springer GitHub ECML PKDD ECML Pres UAI Pres

Prediction Accuracy & Reliability:
Classification and Object Localization under Distribution Shift

Fabian Diet, Moussa Kassem Sbeyti, Michelle Karg

arXiv Springer

Building Bridges between Bayesian Statistics and Deep Learning

Nadja Klein and Moussa Kassem Sbeyti

podcast magazin

Patents

DE102023201734A1 DE102023201735A1 DE102023207709A1 DE102023203027A1
WO2024200136A1 WO2024200137A1 WO2025031549A1
EP4610888A1 EP4610889A1

Podcasts

Bayesian Learning

PhD Thesis

Automated labeling pipeline for 2D object detection