Spring 2023 CS 444 Deep Learning for Computer Vision

Quick links: schedule, assignment submission, quizzes, grades, announcements and discussion, policies, lecture videos


Erik Desmazieres, The Library of Babel

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 deep reinforcement learning. Coursework will consist of programming assignments in Python (primarily PyTorch). Those registered for 4 credit hours will have to complete a project.

Instructor: Svetlana Lazebnik (slazebni -at- illinois.edu)

Lectures: Mondays and Wednesdays, 11:00AM-12:15PM
3039 Campus Instructional Facility
Lectures will be recorded for later asynchronous viewing. Access to recordings will be restricted to students logged into the illinois.edu domain.

TAs: Daniel McKee (dbmckee2), Zitong Zhan (zitongz3), Nikash Walia (nikashw2), James Soole (soole2), Ryan Marten (marten4), Haomeng Zhang (haomeng4)

Instructor and TA office hours: See Campuswire (and always check announcements for any last-minute announcements of changes)

Contacting the course staff: For emergencies and special circumstances, please email the instructor. For questions about lectures and assignments, use the discussion board. For questions about your scores (including regrade requests), email the responsible TAs.

Prerequisites: 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.

Grading scheme:

  • Programming assignments: 80% of the grade for 3-credit students and 60% of the grade for 4-credit students
  • Quizzes: 20% of the grade for 3-credit students or 15% for 4-credit students
    • Four online multiple choice quizzes throughout the semester (will be conducted on Canvas, you will have four days in which each quiz can be completed, though you will have a limited amount of time once you start)
  • Project: 25% of the grade for 4-credit students
  • Participation extra credit: up to 3% bonus on the cumulative course score will be offered for active in-class and discussion board participation
  Be sure to read the course policies!

Schedule (tentative)

Date Topic Assignments
January 18 Past and present of DL: PPTX, PDF Self-study: Python/numpy tutorial
January 23 Overview of DL problems: PPTX, PDF  
January 25 Linear classifiers: PPTX, PDF  
January 30 Linear classifiers cont. (slides above)  
February 1 Linear classifiers cont.: PPTX, PDF Assignment 1 is out
February 6 Nonlinear classifiers: PPTX, PDF  
February 8 Nonlinear classifiers cont.  
February 13 Backpropagation: PPTX, PDF Assignment 1 due February 14
February 15 Convolutional networks: PPTX, PDF Assignment 2 is out
February 20 Convolutional architectures: PPTX, PDF
February 22 Convolutional architectures cont.
February 27 Training in detail: PPTX, PDF  
March 1 PyTorch tutorial: Jupyter notebook  
March 6 Object detection: PPTX, PDF Assignment 2 due March 6
March 8 Dense prediction: PPTX, PDF Project proposals due March 10
Assignment 3 is out
March 20 Self-supervised learning: PPTX, PDF  
March 22 Self-supervised learning cont.  
March 27 Adversarial examples: PPTX, PDF  
March 29 Generative adversarial networks: PPTX, PDF  
April 3 Advanced GAN models: PPTX, PDF Assignment 3 due April 4
April 5 Advanced GAN models cont. Assignment 4 is out
April 10 Image-to-image translation: PPTX, PDF  
April 12 Diffusion models: PPTX, PDF Project progress reports due April 14
April 17 Deep Q-learning: PPTX, PDF  
April 19 Policy gradient methods: PPTX, PDF Assignment 4 due April 19
Assignment 5, extra credit assignment are out
April 24 Recurrent networks: PPTX, PDF  
April 26 Models with attention, transformers: PPTX, PDF  
May 1 Large language models: PPTX, PDF  
May 3 Vision transformers, other trends: PPTX, PDF Assignment 5 due May 5
Extra credit assignment due May 8
Final project reports due May 10

Resources

Other deep learning courses with useful materials

Tutorials

Useful textbooks available online

Statement on mental health

Diminished mental health, including significant stress, mood changes, excessive worry, substance/alcohol abuse, or problems with eating and/or sleeping can interfere with optimal academic performance, social development, and emotional wellbeing. The University of Illinois offers a variety of confidential services including individual and group counseling, crisis intervention, psychiatric services, and specialized screenings at no additional cost. If you or someone you know experiences any of the above mental health concerns, it is strongly encouraged to contact or visit any of the University's resources provided below. Getting help is a smart and courageous thing to do -- for yourself and for those who care about you.

Counseling Center: 217-333-3704, 610 East John Street Champaign, IL 61820

McKinley Health Center:217-333-2700, 1109 South Lincoln Avenue, Urbana, Illinois 61801