EECS 542: Advanced Topics in Computer Vision

This is a seminar-style graduate-level class covering very recent advances in computer vision. The main focus of the class will be on reading and critiquing recent research papers. In each lecture, you will present and critique several recent research papers. You will also explore ideas covered in the course via a final self-directed project. This class is not intended to be an introduction to computer vision or deep learning. There will be no problem sets.

Lectures: Lectures will take place on Monday and Wednesday, 3:00 - 4:30pm. Since this is a discussion-based class, your attendance is required. Missing more than two classes without an excuse will negatively affect your grade. We will take attendance on randomly chosen days.

Attending: The class will be in-person only. Lecture recordings will be available until the end of the course.

Prerequisites: This is an advanced vision course. Students are expected to have taken an introductory vision course before enrolling (EECS 442, 504, or equivalent), so that they will be prepared to read and discuss recent research.

Paper reviews: You'll be required to submit short paper reviews each week (one per class), beginning the week of Lecture 2. Your review should be based on the paper itself, rather than the discussion. It is therefore due before the paper is presented in class (i.e. at 3pm on Monday or Wednesday).

Reviews will be graded as: ✓+, ✓, ✓−, 0. We will not accept late submissions without a valid excuse. However, we will drop your 5 lowest review scores.

Q&A: This course has a Piazza forum, where you can ask public questions. We also appreciate it when you respond to questions from other students. If you have an important question that you would prefer to discuss over email, you may email the course staff (eecs542-w24-staff@umich.edu), or you can contact the instructor by email directly.

Textbooks: In this class, we'll mostly be reading research papers, rather than textbooks. The following might be useful as reference, though:

Presentations: You will give 1-2 presentations throughout the course (depending on enrollment). We will distribute one list of papers during the first week of class, and another a few weeks into the semester. You will rank the list of papers, and we will assign one to you. Most classes will also contain an background talk, which will provide background material to help you understand the papers.

Peer reviews: Your presentation grade will in part be based on peer reviews from other students. You will be randomly assigned to do peer reviews for 3 papers.

GPU computing: For the project, you may require GPUs to train deep learning models. One common option is to use Google Colab. Please note, however, that the free version comes with significant limitations.

Grading: Final grades will be computed as follows:

You will be in charge of teaching one class, as part of a group of 3 people (starting Lec. 4). Each class will be organized around a topic of ongoing research. We'll send up a sign-up sheet after the first class, where you will rank

Organization: We suggest organizing most classes as follows:

The background section is usually the most important part of the class. It should resemble a mini-lecture, covering the "basics" that students will need to understand the paper presentations. For example, if the class is covering papers about recent transformer papers, this section should review what a transformer is, and it should touch on any relevant findings that are necessary to understand the papers. Often, this will involve also describing prior attempts to solve the problems that the (much more recent) papers address.

Each paper section should be a critical presentation the work in the paper. You should explain what problem the researchers were addressing, their motivation for what their solution was, and how well they succeeded at that goal. Unlike introductory courses, where methods are largely well-understood and have passed the "test of time", the papers in this class will often have important limitations. We therefore encourage you to take a critical approach to reading the papers, and to describe possible shortcomings. We also encourage you to discuss things in the paper that you do not think were well-justified, and choices by the authors that you did not understand.

Finally, for the (optional) discussion, you will lead a brief interactive session, where students can debate the issues at stake in the papers. For example, you might run a Q&A session where you ask: should we really consider language-based supervision to be "unsupervised", or do we need to interact with the world to learn good representations?.

Slides: You are allowed to use existing figures, but please clearly credit the authors. Since part of the purpose of the presentation is to have you go through the process of slides, we would like you to make the slides yourself. However, you are permitted to reuse a small number of existing slides (just make it clear that the whole slide was taken from another source). Please submit your slides to us in PDF form. By default, we will post your slides only on Canvas, so that they are only visible to those enrolled in the class. We'd also be happy to post them publicly if you'd like.

Signing up: We'll assign people to presentation timeslots in two phases (i.e. the first and second halves of the class). You'll fill out a questionaire indicating which classes you'd like to participate in. If you happen to have a group of 3 in mind already, please indicate this on the form, and we will try to assign you to a single topic (we unfortunately cannot accommodate groups with other sizes).

You'll do a self-directed group project, due at the very end of the course. Groups should be at most 4 students, unless you are given permission from the instructor. Deliverables include: Please sign up for a presentation timeslot here.