Hide menu

TSBB19 Machine Learning for Computer Vision HT2021

This course runs the first time HT2021. It is based on the TSBB17 course which ran 2020.

The course is given during the HT1 period, and takes place on campus, according to the TimeEdit schedule. Note that not all the time slots in the TimeEdit schedule will be used. A few spare slots have been reserved in case a session has to be moved. These are labelled "Backup lecture/Reservtillfälle".

Registration

Registration

Registration autumn 2021 opens on August 30.

If you intend to take the course, make sure to register ASAP, using the Student portal. You need to be registered on the course to receive course email, and to have results input to Ladok. If you follow the course but are not registered to any program at the University, please contact the course examiner to make sure that you receive email about the course.

Course extent

Course extent

This course is worth 6 ECTS credits, which corresponds to approximately 160h of work per student. The time is divided among the following activities:

More details can be found in the study information for TSBB19.

People

People

Our offices are in the B-building. Lecturers sit in corridor D, first floor between entrances 25 and 27. Project supervisors sit in Visionen.

You can contact us, and your fellow students using the MS Teams Team for TSBB19.

Course Material

Course Material

  • Study information for TSBB19.
    This is the formal course description.
  • Book 1: Goodfellow et al., Deep Learning, MIT Press (2016).
    Relevant contents: Theory on machine learning, convolutional neural networks, loss functions, and regularization.
    The book is available as full pdf. See also Book webpage.
  • Book 2: Richard Szeliski, Computer Vision: Algorithms and Applications, Springer Verlag (2011).
    Relevant contents: classical computer vision, feature extraction, optimization.
    The book is available as an on campus e-book via the LiU library. See also Book webpage.
  • The course has three GIT repositories.
    These are hosted in LiUs GitLab (accessible to anyone with a LiU login). One repository contains the course material (e.g. lecture slides, and articles for background reading), and the other two contain support code for the projects.

Examination

Examination

This course has two examination modules:

  • TEN1 A written examination in English.
    It takes place in October, at the end of the course. Reexamination opportunities are in January, and in August. Registration period, and exact dates for exams can be found using Tentasearch.

    The exam has the same format as the previous course TSBB17. See example exams below:

    • Example exam from 2017-10-17 [pdf]
    • Example solutions from 2018-01-02 [pdf]
  • PRA1 The projects are examined with written reports and oral presentations in English.

Lecture Schedule 2021

Lecture Schedule 2021

All lectures and seminars will take place on Campus Valla according to the schedule below. To find a particular room, you can use this map.

Before the lectures, the lecture slides from last year can be found in the course material repository. Updated slides will be pushed after the lecture has taken place. The repository also contains additional relevant literature for each lecture. The recorded lectures from last year's course can be accessed through the Lisam page for the course.

Date,Time,Room Activity Teacher
August 30: 08.15-10
A35
Lecture 1
Introduction
Per-Erik Forssén
August 31: 10.15-12
A35
Lecture 2
Feature Descriptors and Evaluation
Per-Erik Forssén
September 1: 13.15-15
A25
Lecture 3
Convolutional Neural Networks: Introduction and Theory
Michael Felsberg
September 3: 8.15-10.00
BL32
Lecture 4
Image Classification with Convolutional Neural Networks
Michael Felsberg
September 7: 10.15-12
BL32
Lecture 5
Compound Descriptors and Metric Learning
Per-Erik Forssén
September 8: 13.15-15
A25
Lecture 6
Project 1: Visual Object Recognition
Per-Erik Forssén
September 10: 8.15-10
A25
Lecture 7
Visual Object Detection
Per-Erik Forssén
September 14: 10.15-12
A25
Lecture 8
Visual Object Tracking: Introduction
Michael Felsberg
September 21: 10.15-12
Planck
Lecture 9
Discriminative Correlation Filters for Visual Tracking
Michael Felsberg
September 22: 13.15-15
KY24, KY25
Seminar 1
Presentation of project 1
Per-Erik Forssén
Michael Felsberg
September 22: 15.15-17
T2
Lecture 10
Project 2: Visual Object Tracking
Per-Erik Forssén
October 13: 13.15-15
SH62, SH63
Seminar 2
Presentation of project 2
Per-Erik Forssén
Michael Felsberg

A more extensive schedule can be found in TimeEdit. It also contains scheduled project time (labelled "Projekttid"). These are times when you have exclusive access to the computer rooms Olympen and Asgård. TimeEdit also lists backup lectures. Note that teachers will only be present at activities listed in the table above.

Projects

Projects

The projects are conducted in groups of 5 or 4 students (in order of preference).

Groups and supervisor assignments are finalized at the introductory lecture of project 1, and will be published in the course repository.

General resources

We recommend using the following software:

  • PyTorch A deep learning framework for Python (support code for the projects is written for PyTorch).
  • PyCharm A Python IDE (installed in Olympen and Asgård).
Other related software of interest:
  • OpenCV (Open Source Computer Vision) library that is installed at ISY labs. Python bidnings exist.
  • VLFeat has a a useful code library, both for Matlab and C/C++.
  • LIBSVM A Library for Support Vector Machines (Matlab, Python).

Project repositories

Project code should be developed under versioning control, with changes tracked according to LiU-ID of the participating group members.

  • Project groups should get their repositories from GITLab at LiU
    Note: this is not GitHub, and GitHub should not be used.


Last updated: 2021-09-02