Block-Seminar on Deep Learning for Bio-Medical Data Analysis

apl. Prof. Olaf Ronneberger (DeepMind)

In this seminar you will learn about relevant bio-medical research fields and the most recent methods (mainly based on deep learning) that have been already applied to bio-medical data, or that have a large potential in this field. Especially generative models and unsupervised methods have a large potential to learn concepts from large non-annotated data bases (see a recent blog post from DeepMind on "Unsupervised learning: the curious pupil"). For each paper there will be one person, who performs a detailed investigation of a research paper and its background and will give a presentation. The presentation is followed by a discussion with all participants about the merits and limitations of the respective paper. You will learn to read and understand contemporary research papers, to give a good oral presentation, to ask questions, and to openly discuss a research problem.

Due to the Corona crisis, the seminar will be entirely held online, i.e., the student presentations will be given with a teleconferencing tool using screen sharing, as will be the discussions of the papers.

(2 SWS)
Online via teleconference (unless university reopens)
Contact person: David Hoffmann

Beginning: Watch the following lectures before November 5:
About the seminar
Giving a good presentation
Proper scientific behavior
If you want to participate, register in HisInOne for the course, attend the Zoom meeting on November 5 11:00, and send an email with your name and your paper priorities (B1-B10, favorite paper first) to David Hoffmann before November 9.

Mid-Semester Meeting: t.b.a.
Video conference link will be in the e-mails
Introduction to Neural Networks by apl. Prof. Olaf Ronneberger (DeepMind)

ECTS Credits: 4

Recommended semester:

6 (Bachelor), any (Master)
Requirements: Background in computer vision

Remarks: This course is offered to both Bachelor and Master students. The language of this course is English. All presentations must be given in English.

There is a related Seminar on Current Works in Computer Vision offered by Prof. Thomas Brox

Topics will be assigned for both seminars via a preference voting (detailed information will follow). Please register for the seminar online before the first meeting. If you could not register still come to our introductory online meeting to see if there are papers free. If there are more interested students than places, places will be assigned by a mixture of motivation in the first meeting and priority suggestions of the system. The date of registration is NOT important. In particular, we want to avoid that people grab a topic and then jump off during the semester. Please have a coarse look at all available papers to make an informed decision before you commit. The listed papers are not yet sorted by the time of presentation.

All participants must read all papers and answer a few questions. The questions will be available here. The answers must be sent to the corresponding advisor until t.b.a.. We highly recommend to read and understand all papers first, before you start to prepare your presentation.

Slides of the introductory lecture
Powerpoint template for your presentation (optional)


Time Paper Student   Advisor Slides  
09:15 Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs Andreas Sälinger Artemij Amiranashvili Slides
10:00 Deep Anomaly Detection with Outlier Exposure Rishabh Jain Silvio Galesso
10:45 Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty Yunpeng Wu Osama Makansi Slides
11:30 Deep Residual Flow for Out of Distribution Detection Michel Dehn Özgün Çiçek Slides
12:15 Lunch Break
13:15 Self-Supervised Learning by Cross-Modal Audio-Video Clustering Jonas Grimm Max Argus Slides
14:00 Evolving Losses for Unsupervised Video Representation Learning Salem Ayadi David Hoffmann Slides
14:45 A Simple Framework for Contrastive Learning of Visual Representations Julia Mertesdorf Sudhanshu Mittal Slides
15:30 Coffee Break
15:45 Selecting Relevant Features from a Universal Representation for Few-shot Classification Poojitha Ramachandra Tonmoy Saikia Slides
16:30 MetaFun: Meta-Learning with Iterative Functional Updates Alexander Bitzenhofer Artemij Amiranashvili Slides
17:15 NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis Linus Niedermaier Jan Bechtold
18:00 Discussion
18:30 End of the Seminar