Location: Engineering Hall 2540
Time: Tues, Thurs 9:30-10:45am
Credits: 3
Instructor: Yong Jae Lee
Email: yongjaelee@cs.wisc.edu (email subject should begin with "[CS 839]")
Office hours: By appointment
TA: Haotian Liu
Email: lht@cs.wisc.edu (email subject should begin with "[CS 839]")
Office hours: By appointment
Announcements
(1/25) 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 "see" the visual world (i.e., understand images and videos). It has real-world applications in many areas including content-based search, healthcare, and autonomous vehicles, with visual recognition tasks like image classification and object detection being core to many of those applications. Over the past decade, deep learning has greatly advanced the state-of-the-art in visual recognition research. This graduate course will dive into the fundamentals of deep learning for visual recognition, and survey the state-of-the-art in a broad range of topics including object recognition, activity recognition, and scene understanding. It will be a mix of instructor led lectures and student led presentations. Students will learn to implement their own deep networks for visual recognition, to understand and analyze state-of-the-art techniques, and to identify interesting open questions and future directions. It should be of relevance to students interested in computer vision and machine learning.
Prerequisites
An introductory course in computer vision and/or machine learning. Programming will be required for the final project. Please talk to me if you are unsure if the course is a good match for your background.
Requirements
Students will be responsible for completing two problem sets during the first half of the course, and for the second half of the course, writing paper reviews each week, participating in discussions, presenting once/twice in class (depending on enrollment), and completing a final project.
Canvas
We will use Canvas for assignment, paper review, and project proposal/report submissions and grading. Our class page: https://canvas.wisc.edu/courses/295401
Grading
The final grade will be determined by:
Problem sets (20%)
Paper reviews (20%)
Class participation (10%) (Only for paper presentation days; starting 3/22)
Paper presentation (20%)
Final project (30%)
Important Dates
2/17: Final project proposal due
2/22: Problem Set 1 (PS1) due
3/10: Problem Set 2 (PS2) due
4/28-5/5: Final project presentations
5/6: Final project report due
Detailed course requirements and grading are here.