The lectures take place in KN:E-301 on Monday 14:30-16:00 and the labs take place in KN:E-230 on Monday, Tuesday and Wednesday; see schedule for details. The first seven weeks will be focused on lectures and regular labs with homework, the content of the remaining seven weeks will depend on your decision: You can either continue in regular labs and solve homework, or you can work on your own semestral work. The lecture in the last (14th) week is devoted to the exam test. The points are divided into the three following categories:

- Common homework from the first seven weeks HW1, HW2 (20p),
- Semestral work — OR — compulsory-optional homework HW3, HW4, HW5 (40p),
- Tests (40p).

**Minimum credit requirements: **

- achieve at least one point from each homework (without considering the late submission penalty)
- achieve at least one point from every test

**The final grade will be determined by the total number of points according to the following table**

No. of points | Exam assessment |
---|---|

0-49 | F |

50- 59 | E |

60-69 | D |

70-79 | C |

80-89 | B |

90-100 | A |

All homework will be assigned during the labs; see the lab schedule for the assignment dates. The submission of each homework has a strict deadline. The number of points achieved from the homework will depend on the relative performance of the solution.

Students are encouraged to come up with their own topics of semestral work – just come up with something which will be fun for you (and us), and it is at least somehow connected with deep learning. Nevertheless, we have provided Suggestions for the Topics by our teachers for your inspiration. In both cases, keep in mind that the amount of teacher's help is restricted by the content of this course. In particular, we can help you with explaining “why your classifier does not generalize well on new data” however, we cannot help you with solving problems such as “I have downloaded code from some researcher, and I do not know how to compile it” or “I do not know how to build an application for mobile phone”. ⇒ Choose the semestral work wisely and make sure that any required knowledge is covered sufficiently by your team members. Semestral work is a risky business; in case of failure, the number of points can be lower than from compulsory-optional homework; therefore, we have decided to provide a reward for taking the risk in the form of 0-5 bonus points. In case of a fatal failure, you can always switch to the homework branch.

The suggested size of the team for semestral work is four students. Larger or smaller groups will be allowed in well-justified cases (typically, it is required to explain the role of each student cooperating in the team). You are strongly encouraged to start working on the semestral work from the very beginning (first week) since most of the semestral work topics contain preparation works, which do not require any knowledge gained during the course. To start working, just create a team and present the topic and work plan to the head of the labs (cechjos3@fel.cvut.cz). In case of a both-side-agreement, you can start working immediately.

The presentation of semestral works takes place in the 14th week. There will be 10-minute long oral presentations, which will take place during the labs. Evaluation is based on the lecturers and student voting.

There will be two assessments in total: a mid-term and an exam. These are worth 20 points each, giving a maximum of 40 achievable points in total. Both will take place during Monday Lectures; see schedule for planned weeks. The competencies required for passing the test will be summarized at the end of each lecture.

Karel Zimmermann is the main lecturer of ViR. He is currently an associate professor at the Czech Technical University in Prague. He received his PhD degree in cybernetics in 2008. He worked as postdoctoral researcher with the Katholieke Universiteit Leuven (2008-2009) in the group of prof Luc van Gool. His current H-index is 16 (google-scholar), and he serves as a reviewer for major journals such as TPAMI or IJCV and conferences such as CVPR, ICCV, IROS. He received the best lecturer award in 2018, the best reviewer award at CVPR 2011 and the best PhD work award in 2008. His journal paper has been selected among the 14 best research works representing Czech Technical University in the government evaluation process (RIV). Since 2010 he has been chair of the Antonin Svoboda Award (http://svobodovacena.cz). He was also with the Technological Education Institute of Crete (2001), the Technical University of Delft (2002), and the University of Surrey (2006). His current research interests include learnable methods for robotics.

Josef Čech is the head of the VIR lab. He is a second-year PhD student at the Department of Cybernetics. His main research interests include day-to-night image translation.

Patrik Vacek is the second lab tutor. He is a fourth-year PhD student at the Department of Cybernetics. His main research interests include learning for self-driving cars from unlabelled data.

Simon Pokorny is the lab tutor. He is a master student at Cybernetics and Robotics.

We want students to work individually; therefore, any plagiarism in codes, homework or reports will be punished. We strongly urge each student to read what is/is not plagiarism - we believe that many students will be surprised. In any case, it is not permitted to use the work of your colleagues or predecessors. Each student is responsible for ensuring that his work does not get into the hands of other colleagues. In the case of multiple submissions of the same work, all involved students will be penalized, including those who gave the work available to others.

The above does not apply to semestral works (2nd part of the semester) in which you will be working as a team and can cooperate between teams as well.

courses/b3b33vir/start.txt · Last modified: 2022/09/27 21:21 by pokorsi1