Course information

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, either over Zoom or in person. Since this is a discussion-based class, your attendance is required. Missing more than two classes without an excuse will negatively affect your grade. Recordings are available on Canvas. We will take attendance on randomly chosen days.

Attending: You are welcome to participate in the class either in person or over Zoom. 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).

  • Summarize the paper. For most papers, this means explaining technical contributions, such as key mathematical insights, algorithms, and architectures.
  • Briefly explain how the paper relates to previous work, and why its contributions might be (or might not be) important.
  • Summarize the key experiments.
  • Discuss the paper's shortcomings: e.g. limitations to the methods, unconvincing aspects of experiments, presentation issues.

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-w22-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:

If you have feedback for the author of the Szeliski book draft, please submit it here, and we'll pass it along!

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:

Final project 45%
Reviews 25%
Class presentations 20%
Participation and peer reviews 10%

Academic integrity: While you are encouraged to discuss homework assignment with other students, your programming work must be completed individually. You must also write up your solution on your own. You may not search for solutions online, or use existing implementations of the algorithms. Please see the Michigan engineering honor code for more information.

Support: The counseling and psychological services center (CAPS) provides support for a variety of issues, including mental health and stress.

Presentation guidelines

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:

  1. Background (20 mins)
  2. Paper 1 (20 mins)
  3. Paper 2 (20 mins)
  4. Discussion (20 mins)

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 slides and figures, but please clearly credit the authors. 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. Howeve, 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).

Project guidelines

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:
  • Project proposal (due 1/3 of the way through the semester).
  • Report (4 pages in CVPR format)
  • Presentation (a 5-min talk)
We'll provide more details as the semester progresses.

Staff & Office Hours


Instructor
Name Office hours time
Andrew Owens Tuesday 4:30 - 5:00pm
Max Hamilton Thursday 3:00 - 3:30pm
Office hours will take place over video chat, using the same link as lecture.



Tentative Schedule

Lecture Date Topic Materials
Lec. 1 Wed, Jan. 5 Introduction
    Lec. 2 Mon, Jan. 10 Optical flow
    Lec. 3 Wed, Jan 12 Grouping
    Mon, Jan 17 No class
    Lec. 4 Wed, Jan. 19 Transformers
    Lec. 5 Mon, Jan 24 More transformers
    Lec. 6 Wed, Jan. 26 CNNs
    Lec. 7 Mon, Jan. 31 Video architectures
    Lec. 8 Wed, Feb 2 Object detection models
    Lec. 9 Mon, Feb. 7 Long-tailed object detection
    Lec. 10 Wed, Feb. 9 Tracking
    Lec. 11 Mon, Feb 14 Neural radiance fields
    Lec. 12 Wed, Feb. 16 Neural fields
    Lec. 13 Mon, Feb. 21 Viewpoint prediction
    Lec. 14 Wed, Feb 23 Pose estimation
    Mon, Feb 28 No class
    Wed, Mar 2 No class
    Lec. 15 Mon, Mar 7 Contrastive learning
    Lec. 16 Wed, Mar. 9 Self-supervision without augmentation
    Lec. 17 Mon, Mar. 14 Sound
    Lec. 18 Wed, Mar 16 Language
    Lec. 19 Mon, Mar. 21 Image generation
    Lec. 20 Wed, Mar. 23 Image manipulation
    Lec. 21 Mon, Mar 28 Optimization
    Lec. 22 Wed, Mar. 30 Datasets
    Lec. 23 Mon, Apr. 4 Computational photography
    Lec. 24 Wed, Apr 6 Lighting
    Lec. 25 Mon, Apr. 11 Robotics
    Lec. 26 Wed, Apr. 13 Learning from (or not from) exploration
    Lec. 27 Mon, Apr 18 Ethics