Ines Rieger

Teaching and Research Assistant

M.Sc., Doctoral Candidate

Anschrift:       An der Weberei 5, 96047 Bamberg
Raum:             WE5/04.086

Telefon:          +49-951-863 1686

Email:             ines.rieger(at)

im Vorlesungszeitraum: 
Donnerstag, 14.00 bis 15.00 in WE5/04.086 (Anmeldung per Email wird empfohlen)

außerhalb: nach Vereinbarung


Ines Rieger is a research associate at the Chair for Explainable Machine Learning (xAI) at the University of Bamberg since 2022. Her role encompasses teaching, supervising student thesis’, aiding with writing research grants, and conducting research with a special emphasis on robust AI. In parallel, Ines is pursuing her Ph.D. at the Chair for Cognitive Systems under the supervision of Prof. Dr. Ute Schmid since 2019.

Before joining the University of Bamberg, she worked as a Research Associate at the Fraunhofer Institute IIS for several years. Within the 3-year BMBF project Transparent Medical Expert Companion (TraMeExCo), she developed deep learning-based approaches to estimate modular facial expressions (so-called Action Units) for pain and emotion classification. Her primary objective was to increase not only the classification performance but also the transparency and robustness of such algorithms. Following the project, Ines took on the role of a project manager for a project focused on the development of sensor-based AI, energy-efficient electronics, and satellite-based IoT technology for wildlife research and conservation (GAIA-Sat-IoT). Ines is also a certified scrum master with experience in agile project management for software projects. Furthermore, she gave talks and workshops on deep learning-specific topics to internal and external customers as well as non-expert audiences.

At the University of Bamberg, she completed her Master in Computing in the Humanities M.Sc.


Profiles: Google scholar, ORCID, Research gate, FIS; LinkedIn,

2023 - present                                      

Research associate at the University of Bamberg, Chair for Explainable Machine Learning, Bamberg, Germany

2019- presentPhD candidate at theUniversity of Bamberg, Chair for Cognitive Systems, supervisor: Prof. Dr. Ute Schmid

Research associate at Fraunhofer IIS, Group for Multimodal Human Sensing, Erlangen, Germany


Student research assistant at Fraunhofer IIS, Group for Intelligent Systems, Erlangen, Germany


Working student, IT department at DISAG GmbH & Co KG, Hallstadt, Germany


M. Sc. Computing in the Humanities, University of Bamberg, Germany


Main Research Interests

In general, I am interested in developing cutting-edge methods to increase the robustness, transparency, and fairness of of machine learning algorithms, in particular for deep neural networks.
Specifically, my research objectives are to:

  • Integrate domain knowledge in neural networks as a constraint for facial expression recognition
  • Optimize the distribution of multi-label multi-class datasets and their metadata
  • Detect and mitigate bias in datasets and deep neural networks for facial expression recognition
  • Quantitatively analyze visual explanations
  • Detect and mitigate adversarial attacks on machine learning algorithms
  • Bettina Finzel, Ines Rieger, Simon Kuhn, and Ute Schmid. Domain-Specific Evaluation of Visual Explanations for Application-Grounded Facial Expression Recognition. In Proc. of the International Cross-Domain Conference for Machine Learning and Knowledge Extraction, Springer Nature Switzerland 2023. Link 
  • Ines Rieger, Jaspar Pahl, Bettina Finzel, and Ute Schmid. CorrLoss: Integrating Co-Occurrence Domain Knowledge for Affect Recognition. In Proc. of the 26th International Conference on Pattern Recognition (ICPR), IEEE 2022. Link 
  • Jaspar Pahl, Ines Rieger, Anna Möller, Thomas Wittenberg, and Ute Schmid. Female, white, 27? Bias Evaluation on Data and Algorithms for Affect Recognition in Faces. In Proc. of the Conference on Fairness, Accountability, and Transparency (FAccT), ACM 2022. Link
  • Bettina Finzel, René Kollmann, Ines Rieger, Jaspar Pahl, and Ute Schmid. Deriving Temporal Prototypes from Saliency Map Clusters for the Analysis of Deep-Learning-based Facial Action Unit Classification. In Proc. of the FGKD Workshop at Lernen. Wissen. Daten. Analysen. (LWDA) Conference, 2021. Link 
  • Jessica Deuschel, Bettina Finzel, and Ines Rieger. Uncovering the Bias in Facial Expressions.Kolloquium Forschende Frauen - Gender in Gesellschaft 4.0: Beiträge Bamberger Nachwuchswissenschaftlerinnen, 2021. Award for our contribution of 500 euros. Link 
  • Ines Rieger, Jaspar Pahl, and Dominik Seuss. Unique Class Group Based Multi-Label Balancing Optimizer for Action Unit Detection. In Proc. of the Affective Behavior Analysis in-the-wild (ABAW) Workshop of 15th International Conference on Automatic Face and Gesture Recognition (FG). IEEE, 2020. We won 3rd place in a related challenge. Link 
  • Ines Rieger, René Kollmann, Bettina Finzel, Dominik Seuss, and Ute Schmid. Verifying Deep Learning-based Decisions for Facial Expression Recognition. In Proc. of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning Conf. (ESANN), 2020. Link 
  • Jaspar Pahl, Ines Rieger, and Dominik Seuss. Multi-label Learning with Missing Values using Combined Facial Action Unit Datasets. In Proc. International Conference on Machine Learning (ICML) Conference Workshop The Art of Learning with Missing Values Workshop (ARTEMISS), 2020. Link 
  • Ines Rieger, Thomas Hauenstein, Sebastian Hettenkofer, and Jens-Uwe Garbas. Towards Real-Time Head Pose Estimation: Exploring Parameter-Reduced Residual Networks on In-the-wild Datasets. In Proc. of the 32nd International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems (IEA/AIE), Springer, 2019. Link
  • Ines Rieger. Head Pose Estimation using Deep Learning. Master’s thesis, University of Bamberg, 2018. Link

Thesis Supervision

Please check out our official bidding for thesis topics [Link to VC-Course] or contact me directly via email to request supervision of your Bachelor’s or Master’s Thesis.


  • xAI-Proj-B: Bachelor project Explainable Machine Learning – Dive into Deep Learning


  • xAI-MML-M: Mathematics for Machine Learning - Exercises


  • xAI-Proj-M: Master project Explainable Machine Learning – Deep Learning Life Cycle



  • Award for our contribution to Kolloquium Forschende Frauen, 2021
  • 3rd place in Affective Behavior Analysis in-the-wild (ABAW) Challenge, 2020