Jan Blunk, M.Sc.
Jan Blunk
Address: Computer Vision Group
Department of Mathematics and Computer Science
Friedrich Schiller University of Jena
Ernst-Abbe-Platz 2
07743 Jena
Germany
Phone: +49 (0) 3641 9 46335
E-mail: jan (dot) blunk (at) uni-jena (dot) de
Room: 1224
Links:
Curriculum Vitae
since 2023 Research Associate
Computer Vision Group, Friedrich Schiller University Jena
2021 – 2023 M.Sc. Computer Science
Master Thesis: “Steering Feature Usage During Neural Network Model Training”
Friedrich Schiller University Jena
2019 – 2021 B.Sc. Computer Science
  Bachelor Thesis: “Object Tracking in Wildlife Identification”
Friedrich Schiller University Jena
2018 – 2019 B. Sc. Studies in Computer Science
Christian-Albrecht University of Kiel
Research Interests
  • Trustworthy AI
  • Explainable AI (XAI)
  • Knowledge Integration
Supervised Theses
  • Mattis Dietrich: “Monocular Facial Capture and Reconstruction using 3D-Morphable-Models for Facial Palsy”. Bachelor thesis, 2024 (joint supervision with Tim Büchner)
  • Konstantin Roppel: “Model Feature Attribution for Single Images using Conditional Independence Tests”. Master thesis, 2024 (joint supervision with Niklas Penzel)
Publications
2023
Jan Blunk, Niklas Penzel, Paul Bodesheim, Joachim Denzler:
Beyond Debiasing: Actively Steering Feature Selection via Loss Regularization.
DAGM German Conference on Pattern Recognition (DAGM-GCPR). 2023.
[bibtex] [pdf] [abstract]
2022
Paul Bodesheim, Jan Blunk, Matthias Körschens, Clemens-Alexander Brust, Christoph Käding, Joachim Denzler:
Pre-trained models are not enough: active and lifelong learning is important for long-term visual monitoring of mammals in biodiversity research. Individual identification and attribute prediction with image features from deep neural networks and decoupled decision models applied to elephants and great apes.
Mammalian Biology. 102 : pp. 875-897. 2022.
[bibtex] [web] [doi] [abstract]