Good to see you here!

I am a PhD candidate in the ATLAS Lab, which is a collaboration between the University of Amsterdam and TomTom. The goal of the ATLAS lab, part of the Innovation Center for Artificial Intelligence (ICAI) and Computer Vision Group, is the development new machine learning-based algorithms for high definition map creation for self-driving vehicles. My work is focused on Structured Segmentation, and I am supervised by Prof. dr. Theo Gevers, dr. Martin Oswald and dr. Sezer Karaoglu.

In my work, I mainly focus on leveraging structure and language in visual data and implicitly or explicitly imposing such properties for the tasks of semantic, instance and panoptic segmentation. I explore possibilities to extend traditional segmentation networks with theories of language-, generative- and graph models. Next to my research, I am a teaching assistant in the courses Computer Vision 1, Computer Vision 2 and (have) supervise(d) master AI students Maksymilian Kulicki and Robin Sasse.

Publications

Ulger, O., Kulicki, M., Asano, Y., Oswald, M. R., 2023. Auto-Vocabulary Semantic Segmentation. arXiv preprint [paper] [code]

Ulger, O., Wang, Y., Galama, Y., Karaoglu, S., Gevers, T., Oswald, M. R., 2023. Relational Prior Knowledge Graphs for Detection and Instance Segmentation. In ICCV2023 SG2RL [paper] [code]

Ulger, O., Wiederer, J., Ghafoorian, M., Belagiannis, V., Mettes, P., 2022. Multi-Task Edge Prediction in Temporally-Dynamic Video Graphs. In BMVC2022 [paper]

Ulger, O., Stol, M., Mensink, T., 2018. Evaluating the Effectiveness of Adversarial Patch Attacks on Convolutional Neural Networks. In BNAIC2018 [paper]