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

Welcome to the Advanced Deep Learning for Computer Vision course offered in WS19.

Lecture

Mondays (10:00-11:30) - Seminar Room (02.13.010), Informatics Building

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

ECTS: 8

2V + 3P

Practical

Wednesdays (14:00-15:30) - Seminar Room (02.09.023), Informatics Building

Tutors: Tim Meinhardt, Maxim Maximov, Ji Hou 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

• 21.10 - Lecture 1: Recap of basic concepts of Deep Learning
• 04.11 - Lecture 2: Similarity Learning
• 11.11 - Lecture 3: Attention
• 18.11 - Lecture 4: Neural network visualization and interpretability
• 25.11 - Lecture 5: Autoencoders
• 02.12 - Lecture 6: Bayesian Deep Learning and VAE
• 09.12 - Lecture 7: Generative models I
• 16.12 - Lecture 8: Generative models II
• 13.01 - Lecture 9: Generative models III
• 20.01 - Lecture 10: Videos, autoregressive models, multi-dimensionality
• 27.01 - Lecture 11: Domain Adaptation and Transfer Learning
• 03.02 - Lecture 12: Invited speaker

Practical sessions

• 21.10 - Introduction: presentation of project topics and organization of the course
• 23.10 - Project assignment
• 04.12 - Project Presentations Group 1
• 11.12 - Project Presentations Group 2
• 08.01 - Project Presentations Group 1
• 15.01 - Project Presentations Group 2
• 04.02 - Poster submission deadline (noon)
• 05.02 - Final poster session 13.00 - 16.00

Exam

27.02 from 13.30 - 14.30

Slides

You can now download the slides in PDF format:

• Slides

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.