Summer Semester 2025, TU München

Organiser: Roman Pflugfelder

Computer vision considers models of neural networks initially invented by the machine learning community. This seminar allows the student to study neural networks in more detail. By the end of the seminar, all participants will understand the principles and the applications of selected models, and they will receive the ability to reuse these models as common design patterns in their future work.

This seminar is for Master's students. Attending the course "Introduction to Deep Learning (I2DL) (IN2346)" in advance is recommended. Good scientific programming, e.g., Pytorch, Tensorflow, Jax and Flux, is not mandatory. Analytical skills and interest in paper reading and theory are necessary.

The participants will collect a pool of successful neural networks, network architectures and network layers. After an individual choice, each student will read the respective paper publication to search for and study related papers. Based on the findings, the student will work out a short presentation (15 minutes), which will be given to the group. The students learn collaboratively about the model and the findings within a group discussion and feedback. After the presentations, the student will individually work out his findings, including written feedback, i.e., text, images, and videos. At the end of the seminar, the participants collect all these contributions into a final seminar report.

Assignment to the lab is done via the matching system.

• 11.2.2025: Pre-seminar meeting (4 p.m. - 5 p.m., Zoom Link)
• 23.4.2025: Kick-off meeting (4 p.m. - 5:30 p.m., room 5609.02.023)
• 13.5.2025: Lecture 1 (3 p.m. - 6 p.m., room 5609.03.012)
• 03.6.2025: Lecture 2 (3 p.m. - 6 p.m., room 5609.03.012)
• 01.7.2025 - 02.7.2025 : Presentations (9 a.m. - 12 a.m., room 5609.03.012)
• 23.7.2025: Final meeting (4 p.m. - 5:30 p.m., Zoom)

• Participation during Exercise 1. Own selection of a design pattern (10%)
• Presentation of Exercise 2: structure, slides, clarity, depth, own understanding (30%)
• Contribution to the discussion (20%)
• Exercise 3: Contribution to the seminar report: structure, clarity, originality, understanding (40%)

I will consider your own programmed examples in the grading (+10%)