CS 4476-B / 6476-A Computer Vision
Spring 2022, TR 3:30 to 4:45, Clough 152. Synchronous lecture on Bluejeans
Instructor: James Hays
TAs: Cusuh Ham (head TA), Otis Smith, Pranav Khorana, Sukriti Bhardwaj, Xueqing Li, Yash Kothari, Yoonwoo Kim, Wei Xiong Toh
Course Description
This course provides an introduction to computer vision including fundamentals of image formation, camera imaging geometry, feature detection and matching, stereo, motion estimation and tracking, image classification and scene understanding. We'll explore methods for depth recovery from stereo images, camera calibration, automated alignment, tracking, boundary detection, and recognition. We'll use both classical machine learning and deep learning to approach these problems. The focus of the course is to develop the intuitions and mathematics of the methods in lecture, and then to learn about the difference between theory and practice in the projects.Learning Objectives
Upon completion of this course, students should be able to:- 1. Recognize and describe both the theoretical and practical aspects of computing with images. Connect issues from Computer Vision to Human Vision
- 2. Describe the foundation of image formation and image analysis. Understand the basics of 2D and 3D Computer Vision.
- 3. Become familiar with the major technical approaches involved in computer vision. Describe various methods used for registration, alignment, and matching in images.
- 4. Get an exposure to advanced concepts leading to object categorization and segmentation in images.
- 5. Build computer vision applications.
Prerequisites
No prior experience with computer vision is assumed, although previous knowledge of visual computing or signal processing will be helpful. The following skills are necessary for this class:- Data structures: You'll be writing code that builds representations of images, features, and geometric constructions.
- Programming: Projects are to be completed and graded in Python and PyTorch. All project starter code will be in Python. TA's will support questions about Python. If you've never used Python that is OK, as long as you have programming experience, but you will be playing catch up compared to most students.
- Math: Linear algebra, vector calculus, and probability. Linear algebra is the most important and students who have not taken a linear algebra course have struggled in the past. If you want a refresher on linear algebra, check out Prof. Gilbert Strang's lectures.
Compute Requirements
The institute has minimum compute requirements for all students that you are expected to meet. The projects are somewhat compute intensive, though, so a faster machine will let you iterate more quickly. The institute requirements say nothing about GPUs, though. The deep learning projects can benefit from (but will not require) a GPU. Since we cannot rely on students having GPUs, projects may use cloud services such as Google Colab.Grading
Your final grade will be made up from- 80% 5 programming projects. First project 12% of grade, projects 2 through 5 17% of grade.
- 20% Problem sets / Quizzes.
Final grades will be A/B/C etc for 90.00%+, 80.00%+, 70.00%+, etc.
You will lose 10% each day for late projects. However, you have six "late days" for the whole course. That is to say, the first 24 hours after the due date and time counts as 1 day, up to 48 hours is two and 72 for the third late day. This will not be reflected in the initial grade reports for your assignment, but they will be factored in and distributed at the end of the semester so that you get the most points possible. A late day cannot be split among projects (e.g. half a late day for project 1, and half a late day for project 2). They are used in integer amounts.
If you are taking this course, the expectation is that you have set aside the considerable amount of time needed to get your projects done in a timely manner. These late days are intended to cover unexpected clustering of due dates, travel commitments, interviews, hackathons, computer problems, extracurricular commitments, etc. Don't ask for extensions to due dates because we are already giving you a pool of late days to manage yourself. In fact, we're doubling the pool of late days this semester because of the difficult circumstances. If you are seriously ill and need more time on projects beyond what late days can cover, you should submit documentation to the Dean of Students office and they will reach out to us.
Academic Integrity
Academic dishonesty will not be tolerated. This includes cheating, lying about course matters, plagiarism, code copying, or helping others commit a violation of the Honor Code. Plagiarism includes reproducing the words of others without both the use of quotation marks and citation. Students are reminded of the obligations and expectations associated with the Georgia Tech Academic Honor Code. We will use tools to find code sharing in projects.You are expected to implement the core components of each project on your own, but the extra credit opportunties often build on third party data sets or code. That's fine. Feel free to include results built on other software, as long as you are clear in your handin that it is not your own work.
You should not view, edit, or copy anyone else's code. You should not post code to Canvas, except for starter code or helper code that isn't related to the core project.
More detailed guidance about what is and is not allowed in terms of collaboration with other students:
Allowed
- Talking at the non-code level about project strategies, e.g. "I found it works best if you increase the channel depth of the bottleneck layers". But this does not mean you can collaborate or share answers for the non-code portions of projects and problem sets.
- Explaining concepts or project strategies at the "white board" level, for example drawing out how the SIFT ratio test should work between two sets of keypoints.
- Getting clarification about or working together to better understand anything in the lecture slides.
- Telling another student about a handy function you found. But it would not be allowed to tell them where to insert it in their code, what the arguments to the function should be, etc.
- Telling another student about a debugging strategy.
Not allowed
- Viewing, editing, or copying another student's code for any reason.
- Offering or receiving exact code or hyperparameters, e.g. "Use these parameters for layer 1, these for layer 2, with this learning rate, and this random initial seed..."
- Debugging another student's code.
- Any collaboration on problem sets. Problem sets are to be completed entirely independently.
Getting Help
The projects for this course are substantial and it will be common for students to need clarifications or guidance. Some of the explanation for projects will come from the lecture materials. Some guidance come from the project handout itself. If you are stumped or blocked, you can seek help from other students (within the parameters outlined above), you can ask for help on Piazza (but don't post any code unless your question is private), or you can attend TA office hours. Do not wait until the last few days of a project to post Piazza questions or attend office hours, because the TAs might be swamped.The TAs job is not to debug your code. Do not dump entire source code files onto Piazza asking TAs to fix a bug. Do not hand your laptop to a TA at office hours and ask them to fix your code. The TAs primary goal is to make sure you understand the computer vision concepts necessary to complete the projects. Sometimes there will need to be discussions or troubleshooting at the code level, but don't be surprised if TAs try to minimize such interactions. If you want help from TAs, you should be ready to present the debugging that you've already done, e.g. "On this type of input, here's a visualization of the output that I'm getting".
Over the years, we have refined the projects and added unit tests and autograders so that students can more easily debug their own projects. Unfortunately, this sometimes leads to lazy development patterns. Students will express frustration that "my code passes the unit tests but the autograder gives errors" and expect the TAs to fix this situation. Keep in mind that the unit tests are necessary but not sufficient checks for code correctness. The unit tests help catch some commons errors, but it is expected that code might pass unit tests and fail the autograder if you did not implement something correctly. Even the autograder cannot catch all problems for all projects, because it can be difficult to check the correctness for certain computer vision algorithms. Your code might pass unit tests, get full marks from the autograder, but still have subtle errors that manifest elsewhere in the project. You will have more success in this class if you make an effort to understand the computer vision concepts being taught and not simply optimize for the autograder.
Learning Accommodations
If needed, we will make classroom accommodations for students with documented disabilities. These accommodations must be arranged in advance and in accordance with the office of disability services. (disabilityservices.gatech.edu).Important Links:
- Bluejeans lecture
- Canvas. For announcements, grades, and archived recordings of lecture
- Piazza. For discussion
- Gradescope. For project handin
Contact Info and Office Hours:
If possible, please use Piazza to ask questions and seek clarifications before emailing the instructor or staff.- James: hays[at]gatech.edu
- Cusuh Ham: cusuh[at]gatech.edu
- James: TBD, Bluejeans.
- TA hours: See pinned note in Piazza.
Projects |
| Optional Project 0: Test environment setup. Github |
| Project 1: Convolution and Hybrid images. Github |
| Project 2: SIFT Local Feature Matching. Github |
| Project 3: Camera Calibration and Fundamental Matrix Estimation with RANSAC. Github |
| Project 4: Recognition with deep learning. Github |
| Project 5: Semantic Segmentation. Github |
Textbook
Readings will be assigned in "Computer Vision: Algorithms and Applications, 2nd edition" by Richard Szeliski. The book is available for free online or available for purchase.Syllabus (tentative)
| Class Date | Topic | Slides | Reading |
| Tue, Jan 11 | Introduction to computer vision | pdf, pptx | Szeliski 1 |
|
| |||
| Thu, Jan 13 | Camera Projection and Image Filtering | pdf, pptx | Szeliski 2.1, especially 2.1.4 |
| Tue, Jan 18 | Thinking in Frequency | pdf, pptx | Szeliski 3.2 and 3.4 |
| Thu, Jan 20 | Thinking in Frequency, continued. | pdf, pptx | |
| Tue, Jan 25 | Sampling and Aliasing. Light, cameras, eyes, and color. | pdf, pptx | Szeliski 2.2 and 2.3 |
|
| |||
| Thu, Jan 27 | Interest points and corners | pdf, pptx | Szeliski 7.1.1 and 7.1.2 |
| Tue, Feb 1 | Local image features | pdf, pptx | Szeliski 7.1.3 |
| Thu, Feb 3 | Model fitting, Hough Transform | pdf, pptx | Szeliski 7.4.2 and 2.1 |
| Tue, Feb 8 | RANSAC and transformations | pdf, pptx | Szeliski 8.1 and 2.1 |
|
| |||
| Thu, Feb 10 | Stereo intro | pdf, pptx | Szeliski 12 and 11.2.1 |
| Tue, Feb 15 | Remote guest lecture: John Lambert, GTSFM | ||
| Thu, Feb 17 | Camera Calibration, Epipolar Geometry | pdf, pptx | Szeliski 11 |
| Tue, Feb 22 | Dense Stereo Correspondence | pdf, pptx | Szeliski 12 |
| Thu, Feb 24 | Optical Flow | pdf, pptx | Szeliski 9.4 |
|
| |||
| Tue, Mar 1 | Machine learning crash course | pdf, pptx | Szeliski 5.1 and 5.2 |
| Thu, Mar 3 | Machine learning crash course, part 2 | pdf, pptx | Szeliski 5.1 and 5.2 and 5.3 |
| Tue, Mar 8 | Neural Networks | pdf, pptx | Szeliski 5.3 and 5.4 |
| Thu, Mar 10 | Convolutional Networks and Network Visualization | pdf, pptx | Szeliski 5.3 and 5.4 |
| Tue, Mar 15 | Classical recognition techniques and Deeper Deep Architectures | pdf, pptx | Szeliski 6.2.1 |
| Thu, Mar 17 | ResNet, Big Data | pdf, pptx | |
| Tue, Mar 22 | No lecture, Institute holiday | ||
| Thu, Mar 24 | No lecture, Institute holiday | ||
| Tue, Mar 29 | Guest lecture: Sean Foley | ||
| Thu, Mar 31 | Guest lecture: Amit Raj and Cusuh Ham | ||
| Tue, Apr 5 | Big Data, Crowdsourcing | pdf, pptx | Szeliski 6.3 |
| Thu, Apr 7 | "Unsupervised" Learning and Colorization | pdf, pptx | |
| Tue, Apr 12 | Semantic Segmentation | pdf, pptx | Szeliski 5.5 |
| Thu, Apr 14 | Deep Object Detection and Structured Output from Deep Networks | pdf, pptx | Szeliski 5.4.7 |
| Tue, Apr 19 | 3D Point Processing and Lidar | pdf, pptx | |
| Thu, Apr 21 | Transformer architectures | pdf, pptx | |
| Final Exam Period | Not used. No class or final exam | ||