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

apl. Prof. Olaf Ronneberger (Google 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. 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.

(2 SWS)
Friday, February 24, 2017 (all day, schedule will be announced soon)
Room: 52-2-17
Places: max. 10 students
Contact person: Özgün Çiçek

Introduction: Wednesday, October 19, 2016, 14:15
Room: 52-2-17
Introduction and allocation of seminar topics
Will be held jointly with Seminar on Current Works in Computer Vison

Mid-Semester Meeting: Thursday, December 22, 2016, 16:00-18:00
Room: 52-2-17
Introduction to Neural Networks by apl. Prof. Olaf Ronneberger

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.

Topics will be assigned in the first meeting. Please register for the seminar online before the first meeting. 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 in the first meeting.

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

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

Slides of first session with instructions for a good presentation
Powerpoint template (optional)


Papers (please note that we only have 10 places):

Time (Duration) Paper Presenting student   Advisor Slides
10:00 (40 min) Wide Residual Networks
Making networks wider instead of deeper works very well.
David-Elias Künstle Anton Böhm Slides
10:40 (40 min) Progressive Neural Networks
Transfer learning without forgetting. Nice alternative over a simple fine-tuning which tends to forget the previous task quickly.
Osama Makansi Christian Zimmermann
11:20 (40 min) Discussion
12:00 (60 min) Lunch Break
13:00 (40 min) Adversarial Feature Learning
Interesting approach to learn a reasonable feature representation with adversarial networks.
Ludwig Striet Robert Bensch
13:40 (40 min) Unsupervised Learning of 3D Structure from Images
Nice overview and application of recent conditional generative models.
Andre Biedenkapp Özgün Cicek
14:20 (40 min) Early Visual Concept Learning with Unsupervised Deep Learning
Learning disentangled representations is a key concept for unsupervised learning.
Aditya Bhatt Mohammadreza Zolfaghari
15:00 (40 min) Discussion
15:40 End