15.11.2024 | People | Artificial Intelligence

PhD Defense: Lars Doorenbos Advances Computer Vision with Reliable Processing of Uncertainty

On 15 November 2024, Lars Doorenbos successfully defended his PhD thesis, titled "Reliably Processing Unexpected and Ambiguous Images in Computer Vision." His work addresses one of the most critical challenges in deploying machine learning systems in real-world, safety-critical environments: managing uncertainty effectively. Congratulations to Dr. Lars Doorenbos for his outstanding work and contributions to advancing the field of computer vision!

Lars Doorenbos

Publications:

Zbinden, Lukas; Doorenbos, Lars; Pissas, Theodoros; Huber, Adrian Thomas; Sznitman, Raphael; Márquez Neila, Pablo (2023). Stochastic Segmentation with Conditional Categorical Diffusion Models. In: International Conference on Computer Vision (ICCV) 2023. arxiv. Cornell University 10.48550/arXiv.2303.08888

Jungo, Alain; Doorenbos, Lars; Da Col, Tommaso; Beelen, Maarten; Zinkernagel, Martin; Márquez-Neila, Pablo; Sznitman, Raphael (2023). Unsupervised out-of-distribution detection for safer robotically guided retinal microsurgery. International journal of computer assisted radiology and surgery, 18(6), S. 1085-1091. Springer 10.1007/s11548-023-02909-y