CS444: Deep Learning for Computer Vision (Fall 2023)

Instructor: Saurabh Gupta (saurabhg)
TAs: Anshul Bheemreddy (anshulb3), Chaoran Cheng (chaoran7), Xiaodan Hu (xiaodan8), Yana Zhao (yuanyaz2).
Lecture Times: 11:00AM - 12:15AM on Wednesdays and Fridays
Lecture Location: 1310 Digital Computer Laboratory
Office Hours | Lecture Recordings | Campuswire | Join Campuswire (join using code 5985)

To the extent possible, you should use Campuswire for asking questions. If you have a logistics question specific to yourself, you can email the staff at dlcv-fa23-staff@lists.illinois.edu. If you have a question or concern that you only want to share with the instructor, please email at saurabhg@illinois.edu.

Course Description

This course will provide an elementary hands-on introduction to neural networks and deep learning. Topics covered will include: linear classifiers; multi-layer neural networks; back-propagation and stochastic gradient descent; convolutional neural networks and their applications to computer vision tasks like object detection and dense image labeling; generative models (generative adversarial networks and diffusion models); sequence models like recurrent networks and transformers; applications of transformers for language and vision; and advanced topics (like NeRFs, self-supervision, vision and language). Coursework will consist of programming assignments in Python. Those registered for 4 credit hours will have to complete a project.


Multi-variable calculus, linear algebra, data structures (CS 225 or equivalent), statistics (CS 361, STAT 400, or equivalent). No previous exposure to machine learning is required.

Recommended Textbooks

  1. PML: Probabilistic Machine Learning: An Introduction by Kevin Patrick Murphy (MIT Press, March 2022, Available online)

Grading Scheme

Tentative and subject to changes in the first few weeks.

3-credit 4-credit
Exams 30% 25%
Programming Assignments 70% 50%
Course Project N/A 25%

Up to 1% extra credit for actively participating in class and on Campuswire.


  1. Enrollment works on a first come first serve basis for this class, and I am unable to make exceptions.

  2. If you enroll late, it is your responsibility to catch up with the material. We will not be extending the various assignment deadlines for late enrollment reasons.


This course is largely based on Prof. Svetlana Lazebnik's Deep Learning for Computer Vision course. We would like to thank her and the many researchers who have made their slides and course materials available.