Laines Schmalwasser, M.Sc.
Laines Schmalwasser
Address:Computer Vision Group
 Department of Mathematics and Computer Science
 Friedrich Schiller University of Jena
 Ernst-Abbe-Platz 2
 07743 Jena
 Germany
E-mail:laines (dot) schmalwasser (at) dlr (dot) de
Room:1212
Links: 
Curriculum Vitae
since 2022
 Research Associate / PhD Student
  Computer Vision Group, Friedrich Schiller University Jena &
  Data Analysis and Intelligence Group, DLR Institute of Data Science, Jena
  Topic: “Discover and Explore High-level, Human-interpretable Concepts to Improve
  the Interpretability of Neural Networks”
2020 – 2021
 Research Assistant
  DLR Institute of Data Science, Jena
  Topic: “Exploration, Comparision and Validation of Probability Models and its Data”
2017 – 2020
 M.Sc. Computer Science
  Friedrich Schiller University Jena
  Master Thesis: “How to Visualize Gaussian Mixture Models”
2013 – 2017
 B.Sc. Computer Science
  2015 – 2017: Friedrich Schiller University Jena
  2013 – 2015: Free University Berlin
Research Interests
  • Concept-based Explanations
  • Deep Learning
  • Explainable AI
  • Analyzing Model Training
Supervised Theses
  • Moritz Schwinghammer: “Evaluation of domain interpretability via concept activation vectors for deep learning skin lesion classification”. Master thesis, 2024 (joint supervision with Dr. Sireesha Chamarthi)
  • Christian Ickler: “Feature Steering via Multi-Task Learning”. Master thesis, 2024 (joint supervision with Jan Blunk)
Projects
LOKI: Collaboration of Aviation Operators and AI Systems

In the project Collaboration of Aviation Operators and AI Systems (LOKI), we analyse approaches to collaboration between humans and AI systems. An important building block for this is the investigation of metrics for state detection of the human partners. In the project, we develop prototypes of domain-specific AI systems, such as the digital co-pilot, and use them to develop guidelines for the design of the interface between users and AI systems.

Publications
2025
Laines Schmalwasser, Niklas Penzel, Joachim Denzler, Julia Niebling:
FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks.
International Conference on Machine Learning (ICML). 2025. (Accepted at ICML 2025)
[bibtex] [web] [abstract]
2024
Laines Schmalwasser, Jakob Gawlikowski, Joachim Denzler, Julia Niebling:
Exploiting Text-Image Latent Spaces for the Description of Visual Concepts.
International Conference on Pattern Recognition (ICPR). Pages 109-125. 2024.
[bibtex] [doi] [abstract]