Markus Marks

marks_markus.jpg

I am a postdoctoral scholar in the Vision Group at Caltech, working with Pietro Perona. I specialize in developing machine learning algorithms to enhance scientific discovery in biology and medicine. Leveraging large-scale models and self-supervision, I address the challenges of managing and interpreting the rapidly growing volume of (biomedical) data. My work focuses on reducing human effort in data annotation, minimizing bias, revealing hidden patterns in biomedical data, and developing new methods along the way.

Previously, I finished my Ph.D. at ETH Zurich, where I worked with Mehmet Yanik along with Valerio Mante, Angelika Steger, and Benjamin Grewe on my advisory committee.

selected publications

* denotes equal contribution

  1. mid_level.png
    Probing the Mid-level Vision Capabilities of Self-Supervised Learning
    Xuweiyi Chen, Markus Marks, and Zezhou Cheng
    2024
  2. 7human.gif
    Learning Keypoints for Multi-Agent Behavior Analysis using Self-Supervision
    Daniel Khalil, Christina Liu, Pietro Perona, Jennifer Sun*, and Markus Marks*
    Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2025
  3. ssl_metrics.png
    A Closer Look at Benchmarking Self-Supervised Pre-training with Image Classification
    Markus Marks*, Manuel Knott*, Neehar Kondapaneni, Elijah Cole, Thijs Defraeye, Fernando Perez-Cruz, and Pietro Perona
    2024
  4. tadp.gif
    Text-image Alignment for Diffusion-based Perception
    Neehar Kondapaneni*, Markus Marks*, Manuel Knott*, Rogério Guimarães, and Pietro Perona
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
  5. cellsam.png
    A Foundation Model for Cell Segmentation
    Uriah Israel*, Markus Marks*, Rohit Dilip*, Qilin Li, Morgan Schwartz, Elora Pradhan, Edward Pao, and 7 more authors
    arXiv preprint arXiv:2311.11004, 2023
    under review at Nature Methods
  6. mabe.png
    MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior
    Jennifer J. Sun*, Markus Marks*, Andrew Wesley Ulmer, Dipam Chakraborty, Brian Geuther, Edward Hayes, Heng Jia, and 16 more authors
    In Proceedings of the 40th International Conference on Machine Learning, 23–29 jul 2023
  7. sipec.gif
    Deep-learning-based identification, tracking, pose estimation and behaviour classification of interacting primates and mice in complex environments
    Markus Marks, Qiuhan Jin, Oliver Sturman, Lukas Ziegler, Sepp Kollmorgen, Wolfger Behrens, Valerio Mante, and 2 more authors
    Nature machine intelligence, 23–29 jul 2022
  8. disentanglement.gif
    Robust Disentanglement of a Few Factors at a Time using rPU-VAE
    Benjamin Estermann*, Markus Marks*, and Mehmet Fatih Yanik
    Advances in Neural Information Processing Systems, 23–29 jul 2020