Advanced Deep Learning for Computer vision (ADL4CV) (IN2364)

Welcome to the Advanced Deep Learning for Computer Vision course offered in WS20-21.

Lecture

Lecturers: Prof. Dr. Laura Leal-Taixé and Prof. Dr. Matthias Niessner.

ECTS: 8

2V + 3P

Due to covid-19, all lectures will be recorded!

Practical

Tutors: Ismail Elezi, Guillem Brasó, Yawar Siddiqui and Dave Zhenyu Chen

The practical part of the course will consist of a semester-long project in teams of 2. There will be weekly presentations of the projects throughout the semester.

Lecture

• 02.11 - Course introduction + Lecture 1: Visualization and interpretability
• 06.11 - Lecture 2: Similarity Learning
• 09.11 - Lecture 3: Autoencoders and VAE
• 13.11 - Lecture 4: Graph neural networks
• 16.11 - Lecture 5: Generative Adversarial Networks 1
• 20.11 - Lecture 6: Generative Adversarial Networks 2
• 23.11 - Lecture 7: Autoregressive models
• 27.11 - Lecture 8: Neural rendering
• 30.11 - Lecture 9: Multi-dimensionality

Practical sessions

• 06.11 - Introduction: presentation of project topics and organization of the course
• 13.11 - Project assignment
• 23.11 - Abstract presentation deadline (midnight)
• 11.12 - First Project Presentations Group 1
• 14.12 - First Project Presentations Group 2
• 22.01 - Second Project Presentations Group 1
• 25.01 - Second Project Presentations Group 2
• 08.02 - Report deadline (midnight)
• 12.02 - Final virtual poster session 14.00 - 16.00

Exam

TBA

Slides

You can now download the slides in PDF format:

• Slides

Videos

You can find all videos for this semester here:

• Youtube Playlist

Prerequisites

• Introduction to Deep Learning (I2DL) (IN2346)
• Strong mathematical background: Linear algebra and calculus.
• Previous knowledge of Python is mandatory.
• Previous knowledge of PyTorch is highly recommended.

Moodle

We use Moodle for discussions and to distribute important information. Please check the News and Discussion boards regularly or subscribe to them. The slides and all material will also be posted on Moodle.

Contact us

If you have any questions regarding the organization of the course, do not hesitate to contact us at: adl4cv@dvl.in.tum.de

For questions on the syllabus, exercises or any other questions on the content of the lecture, we will use the Moodle discussion board.