CIS 4930/CIS 5930

Computer Vision - 2024 Fall

Administrivia

  • 📢 Instructor: Dr. Shangqian Gao (sg24bi[at]fsu[dot]edu)
  • 📅 Time: Tuesday & Thursday, 4:50 pm-6:05 pm (ET)
  • 🏫 Location: Classroom Building (HCB) 307
  • 🔍 Office Hour: Tuesday & Thursday, 2:50 pm-4:50 pm (ET)
  • 🎒 Format: In-person only (unless there is a drastic change in the situation).
  • 💡 Teaching Assistants: Ruoyu Li TA Office Hour: Tuesday, 9:30am-11:30am (ET) TA Office: Love 0025A (inside the Majors Lab)

Course Overview

🚀 In this course, students will explore the field of modern computer vision. The curriculum is divided into two main sections: Low-level Vision and High-level Vision. Low-level Vision focuses on classical computer vision methods for extracting basic visual features, and High-level Vision covers more recent advances of computer vision by incoperating deep neural networks to perform complex tasks.

Textbook

Computer Vision: Algorithms and Applications, 2nd ed.

Authors: Richard Szeliski

Deep Learning

Authors: Ian Goodfellow, Yoshua Bengio, Aaron Courville

Grading

Grading Grading will be based on the following components:

  • Homework Assignments (45%) (3 assignments x 15% each = 45%)

  • First Project (20%): The first project will be a from scratch implementation of deep neural networks using a language of your choice. No auto-differentiation package (like Pytorch, Tensorflow, etc.) is allowed to use for this project.

  • Second Project (25%): The second project does not have a specific topic. A good project should either propose a new method for addressing an existing problem or apply techniques we’ve studied in class (or other relevant methods) to a new, unaddressed problem. A borderline project will simply reimplement existing works. Given the GPU-intensive nature of modern computer vision research, we have several options: 1. Department GPUs, 2. Amazon SageMaker Studio, 3. Google Colab.

Students are encouraged to work in groups of three for their final project. You are strongly encouraged to present a project proposal to the instructor during one office hours session. Please use visual aids (e.g., bring slides/figures/tables, and/or draw on the whiteboard during the conversation). The proposal discussion should take place within the first month of the course. This component is not graded. The final project contains two parts: 10% presentation + 15% project report.

  • Participation and Quizs (10%)

  • 🎁 Extra Bonus: (1) Projects with potentials to be submitted to major CV/ML conferences will get extra bonus. Please make an appointment with the instructor for a comprehensive evaluation of the research project for the extra bonus. Each project under the instructor's recognition will gain 10 points on their final grades; (2) Students are highly encouraged to provide feedback on the development of this course. At the end of this semester, a feedback survey completion rate exceeding 70% will lead to an additional 5 points for everyone enrolled in this class.

Schedule

Date Topic Materials Notes
8.27 (Tuesday) Introduction Readings: Szeliski Sec. 1.1, 1.2 Slides
8.29 (Thursday)
9.3 (Tuesday)
9.5 (Thursday) Filtering and texture Readings: Szeliski Sec. 3.1-3.3 Slides HW1 out 9/12
9.10 (Tuesday)
9.12 (Thursday)
9.17 (Tuesday) Feature detection and description Readings: Szeliski 7.1 Slides
9.19 (Thursday)
9.24 (Tuesday)
9.26 (Thursday) Class canceled due to Hurricane Helene
9.31 (Tuesday) Lines, circles and segment Readings: Szeliski Sec. 5.2.1, 5.2.2, 7.2, 7.5, 7.4.2 Slides
10.3 (Thursday) Multiple views Readings: Szeliski Sec 2.1, 3.6.1, 11.3 Slides HW1 due 10/7
10.8 (Tuesday)
10.10 (Thursday) Intro to recognition Szeliski Sec. 5.1, 6.1, 6.2 Slides HW2 out 10/9
10.15 (Tuesday)
10.17 (Thursday)
10.22 (Tuesday) Pytorch and Google Colab Tutorial Tutorial Slides by Ruoyu Slides
10.24 (Thursday) Convolutional neural networks Goodfellow Sec. 4.2, 4.3, Ch. 6 Slides
10.29 (Tuesday)
10.31 (Thursday)
11.5 (Tuesday) Object recognition, detection, segmentation Szeliski Sec. 6.3, 6.4 Slides
11.7 (Thursday)
11.12 (Tuesday) Vision and language, video and motion Szeliski Sec. 5.5.1, 5.5.2, 6.5, 6.6 Slides
11.14 (Thursday)
11.19 (Tuesday)
11.21 (Thursday) Unsupervised learning Szeliski Sec. 5.5.4 Slides
11.26 (Tuesday)
11.28 (Thursday) N/A N/A 🏖️ No class.
12.3 (Tuesday) Unsupervised learning (continued)
12.5 (Thursday) Project Presentation
12.10 (Tuesday) Project Presentation
12.12 (Thursday) Project Presentation
12.13 (Friday) 🚨 Project DDL at 23:59 PM (AoE) N/A Not a class day.

Course Policies

Grade of “I” Policy: Incomplete (“I”) grades should be recorded only in exceptional cases when a student, who has completed a substantial portion of the course and who is otherwise passing, is unable to complete a well-defined portion of a course for reasons beyond the student’s control. Students in these circumstances must petition the instructor and should be prepared to present documentation that substantiates their case.

University Attendance Policy: Excused absences include documented illness, deaths in the family and other documented crises, call to active military duty or jury duty, religious holidays, and official University activities. These absences will be accommodated in a way that does not arbitrarily penalize students who have a valid excuse. Consideration will also be given to students whose dependent children experience serious illness.

Academic Honor Policy: The Florida State University, Academic Honor Policy, outlines the University’s expectations for the integrity of student’s academic work, the procedures for resolving alleged violations of those expectations, and the rights and responsibilities of students and faculty members throughout the process. Students are responsible for reading the Academic Honor Policy and for living up to their pledge to . . . be honest and truthful and . . . [to] strive for personal and institutional integrity at Florida State University. (Florida State University Academic Honor Policy, found at http://fda.fsu.edu/Academics/Academic-Honor-Policy).

For this course, in particular, every student must complete his/her assignments, quizzes, and exams independently. Showing your work to your peers or making it accessible to them is considered academic dishonesty. You are responsible for ensuring that your work is adequately protected and not accessible to others.

Americans with Disabilities Act: Students with disabilities needing academic accommodation should: (1) register with and provide documentation to the Office of Accessibility Services; (2) bring a letter to the instructor indicating the need for accommodation and what type; (3) meet (in person, via phone, email, skype, zoom, etc…) with each instructor to whom a letter of accommodation was sent to review approved accommodations. Please note that instructors are not allowed to provide classroom accommodation to a student until appropriate verification from the Office of Accessibility Services has been provided. This syllabus and other class materials are available in an alternative format upon request. For more information about services available to FSU students with disabilities, contact the: Office of Accessibility Services, 874 Traditions Way, 108 Student Services Building, Florida State University, Tallahassee, FL 32306-4167; (850) 644-9566 (voice); (850) 644-8504 (TDD), oas@fsu.edu, https://dsst.fsu.edu/oas/

Confidential Campus Resources: Various centers and programs are available to assist students with navigating stressors that might impact academic success. These include the following:

  • Victim Advocate Program University Center A, Room 4100, (850) 644-7161, Available 24/7/365, Office Hours: M-F 8-5 https://dsst.fsu.edu/vap

  • University Counseling Center, Askew Student Life Center, 2nd Floor, 942 Learning Way. (850) 644-8255 https://counseling.fsu.edu/

  • University Health Services Health and Wellness Center, (850) 644-6230 https://uhs.fsu.edu/

Free Tutoring from FSU: On-campus tutoring and writing assistance is available for many courses at Florida State University. For more information, visit the Academic Center for Excellence (ACE) Tutoring Services’ comprehensive list of on-campus tutoring options at http://ace.fsu.edu/tutoring or contact tutor@fsu.edu. High-quality tutoring is available by appointment and on a walk-in basis. These services are offered by tutors trained to encourage the highest level of individual academic success while upholding personal academic integrity.

Late Policy and Make-up Exams:

  • Late assignments will not ordinarily be accepted. If, for some compelling reason, you cannot hand in an assignment on time, please contact the instructor as far in advance as possible.
  • No credit will be given to late course projects.
  • No make-up exams (except under extremely unusual circumstances).

Syllabus Change Policy: Except for changes that substantially affect the implementation of the evaluation (grading) statement, this syllabus is a guide for the course and is subject to change with advance notice.

Ackowledgement: The course is devepoed based on CS2770, CS1674 and CS1678 from Univerity of Pittsbugh. All of these courses are taught by Dr. Adriana Kovashka. The course is also based on Dr. Xiuwen Liu’s Computer Vision courses.