Seminar on Current Works in Computer Vision

Prof. Thomas Brox

Computer Vision is a very active research field with many practical applications, for instance in quality control, robotics, or driver assistance systems. The goal of Computer Vision is to imitate the flexibility and robustness of the human visual system. Research has made significant progress in recent years particularly due to deep learning. Almost all research in Computer Vision has shifted to deep learning based methods.
In this seminar we will take a detailed look at some of the most interesting recent works. For each paper there will be one person, who performs a more detailed investigation of a research paper and its background and who 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.

In a poll, the students of the introductory session decided for the online format. We will have the seminar online.

(2 SWS)
Wednesday, 14:00-16:00, online
Contact person: Silvio Galesso

Beginning: If you want to participate, register in HisInOne for the course, attend the introduction meeting on October 19 14:00, and send an email with your name and your paper priorities (S1-S9, favorite paper first) to Silvio Galesso by October 24.

Recommended semester:

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

Remarks: The language in this course is English.

There is a strongly related Blockseminar on Deep Learning offered by apl Prof. Olaf Ronneberger from Google DeepMind. The introduction meeting will be jointly for both seminars.

Topics will be assigned for both seminars via a preference voting (see above). If there are more interested students than places, first priority will be given to students who attended the meeting on Oct. 19. Afterwards, we follow the assignments of the HisInOne system. 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 date of presentation. If you don't attend the meeting (or not send a paper preference) but choose this seminar together with only other overbooked seminars in HisInOne, you may end up without a seminar place this semester.

Students who just need to attend (failed SL from previous semester), need not send a preference for a paper, but just reply with "SL only".

All participants must read all papers and answer a few questions. The questions will be available in the 'Questions' column of the table below at least one week before the corresponding presentation. The answers must be sent to the advisor of the paper before the paper is presented. All participants must attend all sessions.


Seminar organization
Giving a good presentation
Proper scientific behavior

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


Date   Paper Questions  Presenting student   Slides   Advisor
14.12.22 Collapse in (non-)contrastive learning questions Ahmet Selim Canakci slides Yassine Marrakchi
21.12.22 Neural Feature Fusion Fields questions Tjark Behrens slides Jan Bechtold
11.01.23 Unsupervised part discovery questions Aasaipriya Chandran slides Silvio Galesso
18.01.23 Discovering states and transformations in image collections questions Cedric Chabenat slides Maria Bravo
08.02.23 Disentangling visual and written concepts in CLIP questions Varun Nelluri Philipp Schroeppel
08.02.23 Compositional physical reasoning of objects and events questions Cora Hartmann slides Simon Schrodi