EECS 442: Computer Vision

EECS 442 is an introductory computer vision class. Class topics include low-level vision, object recognition, motion, 3D reconstruction, basic signal processing, and deep learning. We'll also touch on very recent advances, including image synthesis, self-supervised learning, and embodied perception.

Lectures:
Lectures will take place Monday and Wednesday, 3:00 - 4:30pm. Attendance will not be required, but it is highly encouraged. We will give short, in-class quizzes. However, these are not worth much of your total grade (2% total), and you may miss several of them without penalty. There are multiple ways to participate:

Discussion section:
This class has two discussion sections. Please note that these sections are completely optional. They generally focus more directly on skills that are directly required for problem sets (e.g., a PyTorch tutorial and a linear algebra refresher). By comparison, the lectures mostly cover the underlying theory and methods.

Prerequisites:

Google Colab: The problem sets will be completed using Jupyter notebooks, generally using Google Colab. While this service is free, it is important to note that it comes with GPU usage limits. You may only use the GPUs on a given Google account for a certain number of hours per day. These limits are due to the fact that GPUs are very expensive. Since none of the problem sets require training large models, you may never encounter these limits. However, we have provided a few suggestions for avoiding them:

1. Reduce your GPU usage by debugging your code on the CPU. For example, after confirming that you can successfully complete a single training iteration without error on the CPU, you can switch to the GPU. You can then switch back to the CPU if you need to debug further errors.
2. Since many of the machines in the CAEN computer labs have NVIDIA GPUs with 4GB or more of RAM, you can connect to them remotely and train deep learning models. We have provided instructions for using these GPUs here. In our experience, this approach is also less reliable, so we recommend using Colab when possible. Also, since the problem sets are designed for Colab, running them here will require minor modifications, which we’ve described in the tutorial.
3. We note that the limit is per account (e.g., UMich email or Gmail account).
4. Consider purchasing Google Colab Pro ($10/month) during the portion of the class where GPUs are required (PS5 and onward; approximately 2 months). For students who would like to use this (optional) service, but are unable to afford it, we have been provided with a small amount of funding from the CSE DEI office. Please send the course staff a private message over Piazza if you would like to learn more about this option.
5. We will provide access to the (more powerful) GPUs that are available on Great Lakes. These can be useful for creating larger models for the final project.

Q&A: This course has a Piazza forum, where you can ask public questions. If you cannot make your post public (e.g., due to revealing problem set solutions), please mark your post private, or come to office hours. Please note, however, that the course staff cannot provide help debugging code, and there is no guarantee that they'll be able to answer all questions — especially last-minute questions about the homework. We also greadly 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 (eecs442-fa24-staff@umich.edu), or you can contact the instructor by email directly.

Homework: There will be homework assignments approximately every week. All programming assignments are to be completed in Python, using the starter code that we provide. Assignments will always be due at midnight (11:59pm) on the due date. The assignments will all be worth approximately equal amounts. Written problems will usually be submitted to Gradescope. You may be asked to annotate your pdf (e.g. by selecting your solution to each problem).

Midterm: There will be a take-home midterm exam. It will take place approximately 2/3 of the way through the semester (date TBD). You will have 24 hours to complete it. The exam will not cover all of the course material: we will give you a list of lectures whose material may be on the exam.

Final project: The final project will be completed in small groups during the last weeks of the class. The direction for this project is open-ended: you can either choose from a list of project ideas that we distribute, or you can propose a topic of your own. A short project proposal will be due approximately halfway through the course. During the final exam period, you'll turn in a final report and give a short presentation. You may use an ongoing research work for your final project, as long it meets the requirements.

In class quizzes: We will include quiz questions in some (not all) lectures to encourage an interactive lecture. That is, there will be 0~3 quiz questions per lecture. We will use iClicker to administer these quizzes. Please use the "iClicker Registration" link on Canvas sidebar to sign up to use free "iClicker" App during the class. Quiz grading will mostly be based on effort. You will get 2 points for answering, or 3 points for correct answer (i.e., you'll get most of the points just for showing up). These in-class quiz questions will be worth only 2% of your final grade. We will allow you to drop your lowest grades on 5 quizzes, so you may miss up to (at least) 5 classes without penalty. Given this drop policy and the very small overall weight for the quizzes on the final grade, we will not grant excused absences for lectures/quizzes.

Textbook: There are no required textbooks to purchase, but we recommend the two optional textbooks:

Acknowledgements: This course uses material from MIT's 6.869: Advances in Computer Vision which is associated with the optional textbook Foundations of Computer Vision. It also includes lecture slides from other researchers, including Svetlana Lazebnik, Alexei Efros, David Fouhey, and Noah Snavely (please see acknowledgments in the lecture slides).

Late policy: You'll have 120 late hours (enough hours for 5 late days) to use over the course of the semester. Each time you use a late hour, you may submit a homework assignment one hour late without penalty. You may distribute these any way you'd like. For example, you can use all of your days at once to turn in one assignment 5 days late, or you can turn each assignment in a few hours late. You do not need to notify us when you use a late hour; we'll deduct it automatically. If you run out of late hours and still submit late, your assignment will be penalized at a rate of 1% per hour. If you edit your assignment after the deadline, this will count as a late submission, and we'll use the revision time to compute late hours (rounded up per assignment).

We will not provide additional late time, except under exceptional circumstances, and for these we'll require documentation (such as a doctor's note). Please note that the late hours are provided to help you deal with minor setbacks, such as routine illness or injury, paper deadlines, interviews, and computer (or Google Colab) problems; these do not generally qualify for an additional extension.

Please note that, due to the number of late days available, there will be a long (2+ week) lag between the time of submission and the time that grades are released. We'll need to wait for the late submissions to arrive before we can complete the grading.

Regrade requests: If you think that there was a grading error, you'll have 9 days to submit a regrade request, using Gradescope. This will be a strict deadline, even for significant mistakes such as missing grades, so please look over your graded assignments!

AI/LLM tools: Please do not use AI tools for coding or writing. In particular, we do not allow the use of Colab’s built-in AI coding features, ChatGPT, and Claude for these purposes. The one exception that we will allow are grammar assistance tools (such as Grammarly).

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

Grading:

Academic integrity: While you are encouraged to discuss homework assignments 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 to use existing implementations of the algorithms in the assignments. Please see the Michigan engineering honor code for more information.