Seminar on Current Works in Computer Vision

Prof. Thomas Brox

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. In this seminar we will take a detailed look at large deep learning models. We will look at language models, which were scaled very successfully in recent years, as well as vision model, which have stayed significantly smaller.
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 the introduction meeting, it was decided that the seminar will be held as an online seminar in Zoom.

Seminar: (2 SWS) Wednesdays, 14:00-15:30 as Online Meeting Contact person: Maria Bravo Beginning: If you want to participate, attend the mandatory online introduction meeting on April 19 14:00, register in HisInOne, and submit your paper preferences using the form before April 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. If there are more interested students than places, first priority will be given to students who attended the introduction meeting. 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. 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. 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.

---

Material:

Giving a good presentation
Proper scientific behavior

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

Papers:

Date	Paper	Questions	Presenting student	Slides	Advisor
07.06.23	LLaMA	questions	Rico Andris		Maria Bravo
14.06.23	Scaling laws for language models	questions	Priyabrat Mishra		Johannes Dienert
21.06.23	GPT-4	questions	Anton Merlin Geburek		David Hoffmann
28.06.23	Large vision model (self-supervised)	questions	Jonghyun Ham		Simon Schrodi
05.07.23	Large vision model (supervised)	questions	Gopalji Gaur		Artur Jesslen
12.07.23	PaLM-E	questions	Diego Fernandez Clausen		Max Argus