CS 639: Deep Learning for Computer Vision
(Spring 2024)
Location: 1111 Humanities
Time: Tues, Thurs 11am-12:15pm
Credits: 3
Instructor: Yong Jae Lee
Email: yongjaelee@cs.wisc.edu (email subject should begin with "[CS 639]")
Office hours: Monday 11am-12pm (zoom, link available on class canvas)
TA: Zhuoran Yu
Email: zhuoran.yu@wisc.edu (email subject should begin with "[CS 639]")
Office hours: Wednesday 1-2pm (zoom, link available on class canvas)
TA: Zeyi Huang
Email: zhuang479@wisc.edu (email subject should begin with "[CS 639]")
Office hours: Friday 1-2pm (zoom, link available on class canvas)
Announcements
(1/23) Please read this website and the detailed course requirements and grading criteria very carefully.
Course Overview
Computer vision is the study of enabling machines to understand the visual world (i.e., images and videos), and has applications in content-based search, healthcare, autonomous vehicles, etc., with visual recognition tasks like image classification, object detection, and segmentation being core to many of those applications. Over the past decade, deep learning has greatly advanced the state-of-the-art in computer vision research. This upper-division undergraduate course will dive into the fundamentals of deep learning for computer vision. Students will learn to implement deep neural networks and learn about the state-of-the-art computer vision research in a broad range of topics including object recognition, activity recognition, and scene understanding.
Prerequisites
Programming, calculus, and linear algebra: (COMP SCI 300, 320 or 367) and (MATH 211, 217, 221, or 275) and (MATH 320, 340, 341, 375, or M E/COMP SCI/E C E 532). Please talk to me if you are unsure if the course is a good match for your background.
Requirements
Students will be responsible for participating in class and on piazza, completing 5 problem sets, and completing a final exam.
Textbook
(Optional) Deep Learning by Ian Goodfellow, Yoshua Bengio, Aaron Courville. (Free electronic copy available at that website)
(Optional) Computer Vision: Algorithms and Applications by Rick Szeliski. (Free electronic copy available at that website)
Canvas
We will use Canvas for problem set submissions and grading. Our class page: https://canvas.wisc.edu/courses/395330
Piazza
Rather than emailing questions to the teaching staff, please post your questions on Piazza: https://piazza.com/wisc/spring2024/sp24compsci639001/home
While we encourage you to help your fellow students, please do not post assignment solutions.
Grading
The final grade will be determined by:
Piazza participation (3%)
Problem sets (70%)
Final exam (27%)
Important Dates
2/6: Problem Set 0 (PS0) due
2/22: Problem Set 1 (PS1) due
3/14: Problem Set 2 (PS2) due
4/10: Problem Set 3 (PS3) due
4/26: Problem Set 4 (PS4) due
5/5: Final exam
Detailed course requirements and grading are here.
Acknowledgements
Thanks to Ian Goodfellow, Yoshua Bengio, Aaron Courville, and Rick Szeliski for making their textbooks available online for free. I am also grateful to the instructors of Stanford's CS231n for making their course slides publicly available.