Steffen Czolbe

PhD-Fellow @ University of Copenhagen

I am a PhD Fellow of Machine Learning with the Department of Computer science at the University of Copenhagen, co-advised by Aasa Feragen and Oswin Krause.

My PhD research focuses on developing deep learning methods for medical imaging, with a focus on image registration. In my work I dive into unsupervised & semi-supervised learning, with an emphasis on the registration of tricky, real-world anatomies and an ambition to develop general algorithms that apply to a multitude of problem domains and modalities. I also published on uncertainty quantification and topology detection.

Previously, I obtained a M.Sc. in computer Science from the University of Copenhagen. During my Masters I worked tgether with the LEGO group on teaching reinforcement learning with LEGO Mindstorms Robots, and designed a lightweight perceptual similarity metric for image generation and distance measuring, advised by Christian Igel.


Nov 11, 2021 My paper on topological change detection in images has been accepted to NeurIPS 2021! check out the summary here
Nov 8, 2021 My revamped website is online! 🎉
Jul 9, 2021 I am honored to be awarded Best Paper Runner Up at MIDL2021 for my paper on semantic similarity metrics

Selected publications

Find the full list here
  1. NeurIPS
    A Loss Function for Generative Neural Networks Based on Watson’s Perceptual Model
    Czolbe, Steffen, Krause, Oswin, Cox, Ingemar, and Igel, Christian
    In Advances in Neural Information Processing Systems Dec 2020
  2. NeurIPS
    Spot the Difference: Detection of Topological Changes via Geometric Alignment
    Czolbe, Steffen, Feragen, Aasa, and Krause, Oswin
    In Advances in Neural Information Processing Systems Dec 2021
  3. MIDL Award
    Semantic similarity metrics for learned image registration
    Czolbe, Steffen, Krause, Oswin, and Feragen, Aasa
    Best Paper Award Runner-Up
    In Proceedings of Machine Learning Research Jul 2021