Schedule

Lecture Date Topic Materials Assignments
Lec. 1Mon, Aug. 31A simple vision system
About the course
Cameras
Simple edge detection
ps1 out (filtering)
Lec. 2Wed, Sep. 2 Image filters
Convolution
Gradient filters
Blurring
Sec. 1Fri, Sep. 4 Linear algebra
Mon, Sep. 7 No class
Lec. 3Wed, Sep. 9 Nonlinear filtering
Laplacian
Hybrid images
Template matching
Bilateral filtering
Sec. 2Fri, Sep. 11More linear algebra
Lec. 4Mon, Sep. 14Frequencies
Image statistics
Fourier transform
Lec. 5Wed, Sep. 16Image pyramids
Gaussian pyramid
Laplacian pyramid
Resampling
ps1 due
ps2 out (frequency)
Sec. 3Fri, Sep. 18Fourier tutorial
Lec. 6Mon, Sep. 21Machine learning
Nearest Neighbor
Linear regression
Overfitting
Lec. 7Wed, Sep. 23Linear classifiers
Logistic regression
Stochastic gradient descent
ps2 due
ps3 out (intro to ML)
Sec. 4Fri, Sep. 25Learning tutorial
Lec. 8Mon, Sep. 28Neural networks
Nonlinearities
Network structure
Regularization
Lec. 9<Wed, Sep. 30Optimization
Computation graphs
Backpropagation
Momentum
ps3 due
ps4 out (backpropagation)
Sec. 5Fri, Oct. 2PyTorch tutorial
Lec. 10Mon, Oct. 5 Convolutional networks
Convolution layers
Pooling
Normalization
Lec. 11Wed, Oct. 7 Scene understanding
Scene recognition
Semantic segmentation
ps4 due
ps5 out (scene recognition)
Sec. 6Fri, Oct. 9Office hours
Lec. 12Mon, Oct. 12Object detection
Sliding window
Region-based CNNs
Instance segmentation
Lec. 13Wed, Oct. 14Image synthesis
Texture synthesis
GANs
Conditional GANs
ps5 due
ps6 out (image synthesis)
Sec. 7Fri, Oct. 16Office hours
Lec. 14Mon, Oct. 19Temporal models
3D CNNs
RNNs
Attention
Lec. 14Wed, Oct. 21Language
Autoregressive models
Attention
Captioning
ps6 due
ps7 out (object detection)
Sec. 8Fri, Oct. 23Office hours
Lec. 16Mon, Oct. 26Representation learning
Transfer learning
Autoencoders
Self-supervision
Lec. 17Wed, Oct. 28Multimodal learning
proposal info out
Sec. 9 Fri, Oct. 30Project office hours
Lec. 17Mon, Nov. 2Image formation
Plenoptic function
Pinhole cameras
Homogeneous coordinates
Projection matrix
Lec. 18Wed, Nov. 4 Multi-view geometry
Triangulation
Epipolar lines
Homographies
Warping
ps7 due
ps8 out (self-supervised learning)
Sec. 10Fri, Nov. 6 Project office hours
Lec. 19Mon, Nov. 9 Fitting geometric models
Feature matching
RANSAC
final project guidelines
Lec. 20Wed, Nov. 113D reconstruction
Structure from motion
Multi-view stereo
Stereo algorithms
ps8 due
ps9 out (panoramic stitching)
Sec. 11Fri, Nov. 13Geometry tutorial
Lec. 21Mon, Nov. 16Color (Lecturer: Haozhu Wang)
Color perception
Color constancy
Lec. 22Wed, Nov. 18Motion
Optical flow
Aperture problem
Multi-scale estimation
ps9 due
project proposal due
ps10 out (motion)
Sec. 12Fri, Nov. 20Project office hours
Thanksgiving break
Lec. 23Mon, Nov. 30Light and shading
Shape from shading
Photometric stereo
Intrinsic images
Lec. 24 Wed, Dec. 2Embodied vision
Learning from demonstrations
Reinforcement learning
Sec. 14 Fri, Dec. 4Project office hours
    Lec. 28Mon, Dec. 7Bias and fake images
    ps10 due


    Staff & Office Hours


    Instructor
    Graduate student (GSI)
    Graduate student (GSI)
    Graduate student (GSI)

    Name Office hours times
    Haozhu Wang Thursday 9-10pm
    Zhengyu Huang Tuesday 4-5pmWednesday 1:45 - 2:45pm
    Hansal Shah Tuesday 2-3pmFriday 5-6pm
    Andrew Owens Monday 4:45 - 5:15pm Friday 3pm-4pm
    Office hours will take place over video chat, using the same Zoom link as lecture. When you join the call, you will be put on a waiting list. You will then meet one-on-one with a member of the course staff.


    Course information

    EECS 442 is an advanced undergraduate-level 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 over Zoom on Monday and Wednesday, 3:00 - 4:30pm. Attendance will not be required; we'll post lecture recordings online for people who can't make it. See here for the Zoom link. Please do not share the link, so that we can avoid Zoom bombing.
    • We hope that you'll participate in class! If you have a question during lecture, we reccomend that you use the "raise hand" feature, then unmute yourself when we call on you, or send a message.

    Discussion section:
    This class has two discussion sections, which both use the same Zoom link as the lecture:

    • Friday, 10:30am - 11:30am
    • Friday, 12:30pm - 1:30pm
    Some weeks, we'll host tutorials during these sections, where GSIs will cover a topic in depth (e.g. a PyTorch guide). These tutorials appear in the schedule. Attendance to these tutorials is optional, and recordings will be posted online. Other weeks, the discussion section will function as additional office hours and project discussion.

    Prerequisites:

    • This course puts a strong emphasis on mathematical methods. We'll cover a wide range of techniques in a short amount of time. Knowledge of linear algebra is highly encouraged. Please consider taking a linear algebra course before taking this class; otherwise, it may be quite difficult. For a refresher, please see here. This material should mostly look familiar to you.
    • This class will require a significant amount of programming. All programming will be completed in Python, using numerical libraries such as numpy, scipy, and PyTorch. The problem sets will be completed using Jupyter notebooks, generally using Google Colab. In some assignments, we'll give you starter code; in others, we'll ask you to write a large amount of code from scratch.

    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 last-minute homework questions before the deadline. 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 (eecs442-fa20-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).

    Final project: In lieu of a final exam, we'll have final project. This 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.

    Textbook: There are no required textbooks to purchase. As an experiment, we'll be using a new draft version of the online book:

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

    The following textbooks may also be useful as references:

    • Goodfellow, Bengio, Courville. Deep Learning. (available for free online)
    • Forsyth and Ponce. Computer Vision: A Modern Approach.
    • Hartley and Zisserman. Multiple View Geometry in Computer Vision.

    Acknowledgements: This course draws heavily from MIT's 6.869: Advances in Computer Vision by Antonio Torralba, William Freeman, and Phillip Isola. 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 7 9 late days to use over the course of the semester. Each time you use one, you may submit a homework assignment one day late without penalty. You are allowed to use multiple late days on a single assignment. For example, you can use all of your days at once to turn in one assignment a week late. You do not need to notify us when you use a late day; we'll deduct it automatically. If you run out of late days and still submit late, your assignment will be penalized at a rate of 30% per day. If you edit your assignment after the deadline, this will count as a late submission, and we'll use the revision time as the date of submission (after a short grace period of a few minutes). We will not provide additional late time, except under exceptional circumstances, and for these we'll require documentation (e.g., a doctor's note). Please note that the late days are provided to help you deal with minor setbacks, such as routine illness or injury, paper deadlines, interviews, and computer problems; these do not generally qualify for an additional extension.

    Please note that, due to the number of late days available, there will a lag between submission and grading times — we'll need to wait for the late submissions to arrive before we can finish grading.

    Regrade requests: If you think 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!

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

    Grading:

    • Grades will be computed as follows, with all homeworks equally weighted:
      Homework 70%
      Final project 30%
    • We'll use these approximate grade thresholds:
      A+ TBD
      A 92%
      A- 90%
      B+ 88%
      B 82%
      B- 80%
      C+ 78%
      C 72%
      C- 70%
      These are lower bounds on letter score grades. For example, if you get an 81%, you will be guaranteed to get a B-. We may gently curve the class up, in a way that would only improve your letter grade: e.g. after the curve, an 81% might round up to a B, but it would not round down to a C+.

    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.