Institute of Media Informatics

Alex Bäuerle, M. Sc.

I completed my masters degree at the Institute of Media Informatics 2017 before joining the research group Visual Computing. Since then, I work on visualization in the domain of artificial intelligence.

Research interests

  • Neural Network Visualization
  • Explainable AI
  • AI Fairness

Lectures

I supervise(d) the following lectures:

  • Deep Learning for Graphics and Visualization (WS 19/20)
  • Projekt/Anwendungsfach Data Visualization (reoccuring)
  • Seminar Techniken zur visualisierung Neuronaler Netze (SS 18)
  • Interaktive Computergrafik (WS 17/18)

Theses and Projects

I would gladly supervise theses from the field of neural networks. I am especially interested in generating visualizations of networks, training results and training data. We can, however, also discuss other topics in the field of neural Networks via mail or in my office.

Important: The selection of projects that can be found below is only a subset of possibilities. Working on your own ideas is always possible. Also, most of the time, I have some additional projects ready to be tackled. Therefore, it's always worth making a personal appointment.

Open Topics

  • CAV Sanity

    Concept Activation Vectors (CAVs) are widely used to find out what a network is interested in when making a classification. These are obtained by a manually selected set of examples that are divided in context images and non-context images. However, do these activation vectors really always represent the contexts we are searching for?

  • Explaining Reinforcement Learning

    Reinforcement Learning is really interesting, and gained traction with its application to robots, board games, and even modern video games.

    Currently, reinforcement learning lacks a common debugging and visualization tool. Such a tool could provide a unified interface across different tasks and problems.

  • CompareNN

    Neural networks have evolved a lot over time. There have been different architectures used over time and new problems and techniques have emerged. Comparing these is a tedious task, especially when not trained on the same dataset.

    This work should give a historic overview of the development of these Networks and make comparing them possible. The interactive visualization should respect different properties of the network and make them easily comparable. It should be publicly accessible and thus web-based.

  • PointNet Visualization

    PointNets are used to train neural networks on pointclouds. While there are many visualization techniques for image-based neural networks, PointNets are lacking such visualizations.

    This work aims at providing such visualizations for PointNets. It includes reading up on existing visualization techniques for ImageNets, but should also contain the elaboration of new visualization options for these types of networks.

Completed Projects

  • Respiratory Motion Detection

    This master thesis which was submitted by Christoph Baldauf with the title "Convolutional Neural Networks (CNN) Applied to Respiratory Motion Detection"  was done in cooperation with the centre for translational imaging. During TAVI procedures, the patient is supervised with imaging technology throughout the whole operation. To support doctors, overlays on these images are used. Since the patient is breathing however, there overlays are not always positioned correctly.

    To compensate this, a neural network was trained to recognize and compensate the vertival movement of the chest, and this way reposition such overlays.

  • Crossover Detection

    In cooperation with the Institute of Protein Biochemnistry, this project was aimed to automatically detect crossovers in micro-ct scans of fibrils. These crossovers are important for analyzing and reconstructing the scanned fibrils.

    To enable this automatic localization of crossovers, a neural network for semantic segmentation of fibril images was trained as a student project.

Publications

2020

4.
A. Bäuerle, H. Neumann and T. Ropinski, "Classifier-Guided Visual Correction of Noisy Labels for Image Classification Tasks" , Computer Graphics Forum, 04 2020. Classifier-Guided Visual Correction of Noisy Labels for Image Classification Tasks.
File:https://www.uni-ulm.de/fileadmin/website_uni_ulm/iui.inst.100/institut/Papers/viscom/2020/baeuerle_classifier_guided_correction.pdf

2019

3.
M. Weber, A. Bäuerle, M. Schmidt, M. Neumann, M. Fähndrich, T. Ropinski and V. Schmidt, "Automatic identification of crossovers in cryo‐EM images of murine amyloid protein A fibrils with machine learning" , Journal of Microscopy, Dec. 2019. John Wiley & Sons Ltd.
DOI:10.1111/jmi.12858
File:https://www.uni-ulm.de/fileadmin/website_uni_ulm/iui.inst.100/institut/Papers/viscom/2019/automatic_identification_of_crossovers_in_cryo-em_images_of_mourine_amyloid_protein_a_fibrils_with_machine_learning.pdf
2.
C. Baldauf, A. Bäuerle, T. Ropinski, V. Rasche and I. Vernikouskaya, "Convolutional neural network (CNN) applied to respiratory motion detection in fluoroscopic frames" , International Journal of Computer Assisted Radiology and Surgery, vol. 14, pp. 14-15, May 2019.
DOI:10.1007/s11548-019-01969-3
File:https://www.uni-ulm.de/fileadmin/website_uni_ulm/iui.inst.100/institut/Papers/viscom/2019/CNN_applied_to_respiratory_motion_detection.pdf
1.
A. Bäuerle, C. van Onzenoodt and T. Ropinski, "Net2Vis: Transforming Deep Convolutional Networks into Publication-Ready Visualizations" , arXiv:1902.04394, 2019. https://arxiv.org/abs/1902.04394.
v