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

Welcome to the Advanced Deep Learning for Computer Vision course offered in WS18/19.

Lecture

Mondays (10:00-12:00) - Seminar Room (02.13.010), Informatics Building

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

ECTS: 8

2V + 3P

Practical

Fridays (15:00-17:00) - Seminar Room (02.13.010), Informatics Building

Tutors: Qunjie Zhou and Ji Hou

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.

Content

• 22.10 - Lecture 1: Recap of basic concepts of Deep Learning
• 29.10 - Lecture 2: Similarity Learning
• 05.11 - Lecture 3: Advanced Deep Learning architectures II
• 19.11 - Lecture 4: Neural network visualization and interpretability
• 26.11 - Lecture 5: Bayesian Deep Learning
• 03.12 - Lecture 6: Autoencoders
• 10.12 - Lecture 7: Generative models I
• 17.12 - Lecture 8: Generative models II
• 14.01 - Lecture 9: Autoregressive architectures, CNN vs RNN
• 21.01 - Lecture 10: Recurrent Networks for Visual Q\&A, cross-domain DL
• 28.01 - Lecture 11: Multi-dimensional Deep Learning

• 04.02 - Lecture 12: Domain Adaptation and Transfer Learning

• 01.03 - Exam, 13:30 - 14:30, MW 0001 and MW 2001
• 18.04 - Retake Exam, 08:00 - 09:00, MW 001

Slides

You can now download the slides in PDF format:

• Lecture 1, Lecture 2, Lecture 3, Lecture 4, Lecture 5, Lecture 6, Lecture 7, Lecture 8, Lecture 9, Lecture 10, Lecture 11

Prerequisites

• Introduction to Deep Learning course (IN2346)
• Strong mathematical background: linear algebra, 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.

Project teams and Presentation schedule

• 19.10 - Lecture 0: Introduction to the projects.
  • 26.10 - Meeting to discuss the projects.
• 04.11 - Delivery deadline (midnight) of a 1 page abstract of your project proposal
• 23.11 - Presentation of First Results, Groups 1
• 30.11 - Presentation of First Results, Groups 2
• 07.12 - Presentation of First Results, Groups 3
• 11.01 - Presentation of Final Results, Groups 1
• 18.01 - Presentation of Final Results, Groups 2
• 25.01 - Presentation of Final Results, Groups 3
• 07.02 (still to be confirmed) - Poster session, public presentation of your projects

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.

External (non-TUM) Students

We want to provide access to our lecture for as many students as possible. Therefore, we ask external students that are not TUM students and do not have access to TUMonline to register to Moodle and send us their student information via email. We will then add you to our Moodle course where you will find addtional information and all the course material.