Miaomiao Zhang
CS / ECE 4501 / CS 6501 / ECE 6782: Machine Learning in Image Analysis
Description: This course focuses on an in-depth study of advanced topics and interests in image data analysis. Students will learn practical image techniques and gain mathematical fundamentals in machine learning needed to build their own models for effective problem solving. Topics of image denoising/reconstruction, deformable image registration, data dimensionality reduction, generative models, and deep neural networks for image segmentation/classification will be covered. The main focus might change from semester to semester. The graduate students (CS 6501 / ECE 6782) will be given additional programming tasks and more advanced theoretical questions.
Mathematical background in linear algebra, multivariate calculus, probability and statistics, and programming skills are required in this class.
Class meetings: MW 2:00pm - 3:15pm
Class location: Thornton E316 (lectures will be recorded)
Instructor: Miaomiao Zhang (mz8rr -at- virginia.edu)
Teaching Assistant: Jerry Xing (jx8fh -at- virginia.edu);
Office hours: TTh 1-3pm (TA: Jerry Xing); Fridays 4pm-5pm (Instructor);
Office hour location: TTh (Rice Hall 303); F (Rice Hall 300).
Lecture materials including slides and notes will be posted on UVA Canvas.
Grading
* Projects (3 course projects and 1 final project) (20% * 3 + 10% final project presentation + 15% final project report + 15% final project implementation)
No exams are required in this course.
All programming will be in Python.
All reports must be written in LaTeX and submitted as a s ingle PDF.
Homeworks are due by midnight (11:59:59 PM) on the due date. Late penalty will be applied: 10% off (1 day), 20% off (2 days), 30% off (3 days). Late submissions are not accepted after three late days.
Schedule
| Date | Topics | Projects |
| Week 1 | Aug 27 | Course Introduction |
| Week 2 | ||
| Sep 2 | Introduction to Image Analysis and Basic Variational Methods | |
| Sep 4 | Image Denoising I: Total Variation | PS1 Release |
| Week 3 | ||
| Sep 9 | Image Denoising II: Convolution, Fourier Transformation | |
| Sep 11 | Basics of Image Registration | |
| Week 4 | ||
| Sep 16 | Deformable Image Registration | |
| Sep 18 | Roundtable Paper Reading and Discussion (papers will be uploaded online) | PS1 Due |
| Week 5 | ||
| Sep 23 | Population studies: Fréchet Mean Image; Deformation-based Shape Representation from Images | PS2 Release |
| Sep 25 | Image Data Dimensionality Reduction: Principal Component Analysis (PCA) | |
| Week 6 | ||
| Sep 30 | Nonlinear PCA Methods; Kernel Trick | |
| Oct 2 | Maximum likelihood (MLE) / Maximum a Posteriori (MAP) | |
| Week 7 | Oct 7 | Sampling Methods: Markov Chain Monte Carlo |
| Oct 9 | No Class (Instructor Travel) | PS2 Due |
| Week 8 | ||
| Oct 14 | Reading days (no class) | |
| Oct 16 | Image Data Augmentation / Synthesis | PS3 Release |
| Week 9 | ||
| Oct 21 | Roundtable Paper Reading and Discussion (papers will be uploaded online) | |
| Oct 23 | Neural Networks, Back Propagation | |
| Week 10 | ||
| Oct 28 | Image Regression / Classification: Convolutional Neural Networks | |
| Oct 30 | Image Segmentation: UNet & Transformer | PS3 [Part I] Due |
| Week 11 | ||
| Nov 4 | (Variational) AutoEncoders | |
| Nov 6 | Basics Of Generative Diffusion Models | Final Project Release |
| Week 12 | ||
| Nov 11 | Generative Diffusion Models With Text Instructions | PS3 [Part II] Due |
| Nov 13 | Multitask Learning | |
| Week 13 | ||
| Nov 18 | Adversarial Learning and Domain Adaptation | |
| Nov 20 | Roundtable Paper Reading and Discussion (papers will be uploaded online) | |
| Week 14 | ||
| Nov 25 | Final project presentation I | |
| Nov 27 | Thanksgiving break (no class) | |
| Week 15 | ||
| Dec 2 | Final project presentation II | |
| Dec 4 | Final project presentation III | |
| Week 16 | ||
| Dec 10 | Final project Due |
Disclaimer
The instructor reserves the right to make changes to the course schedule, syllabus, and project deadlines. Changes will be announced early in advance.
Honor Code (Adapted from Honor Syllabus Example Statement of UVa)
I expect students in this class to fully comply with all of the provisions of the University’s Honor Code. By enrolling in this course, you are requested to abide by and uphold the Honor System of the University of Virginia and policies specific to this course by default. All suspected violations will be forwarded to the Honor Committee, and you may, at my discretion, receive an immediate zero on that assignment regardless of any action taken by the Honor Committee. Please let me know if you have any questions regarding the course honor policy. If you believe you may have committed an Honor Offense, you may wish to file a Conscientious Retraction by calling the Honor Offices at (434) 924-7602. For your retraction to be considered valid, it must, among other things, be filed with the Honor Committee before you are aware that the act in question has come under suspicion by anyone. More information can be found at https:honor.virginia.edu/.
ChatGPT & Generative AI Tools Policy
Large language models, such as ChatGPT, and other generative artificial intelligence (AI) tools may be used for any assignment with appropriate citation. Examples of citing these models are available here. You are responsible for fact checking statements composed by AI language models.
Students With Disabilities or Learning Needs
It is my goal to create a learning experience that is as accessible as possible. If you anticipate any issues related to the format, materials, or requirements of this course, please meet with me outside of class so we can explore potential options. Students with disabilities may also wish to work with the Student Disability Access Center to discuss a range of options to removing barriers in this course, including official accommodations. Please visit their website for information on this process and to apply for services online: sdac.studenthealth.virginia.edu. If you have already been approved for accommodations through SDAC, please send me your accommodation letter and meet with me so we can develop an implementation plan together.
Recording of Classroom Activities
Every lecture will be recorded to accommodate students who are not able to join in-person. These recordings can only be used for the purpose of individual or group study with students enrolled in this class during this semester. You may not distribute them in whole or in part through any other platform or to any person outside of this class, nor may you make your own recordings of this class, unless the instructor and all students who are present have been informed that recording will occur. For more details, please refer to UVA Provost Policy-008.