CS 6476 Computer Vision
(Fall 2023)
Course Description
This is an updated graduate-level introduction course to computer vision, with a focus on modern computer vision topics, especially deep learning based visual recognition, generative modeling, transformers, and diffusion models. At the end of the lectures we also include a quick introduction to classic vision topics.
ScheduleΒ
Lectures
Tue Aug 22, L1: Introduction
Thu Aug 24, L2: Modern Vision, ML Basics & A Neuron
Tue Aug 28, L3: Neural Nets & Convolutional Nets
Thu Aug 31, L4: Deep Neural Architectures
Tue Sep 05, L5: ResNets
Thu Sep 07, L6: Object Detection I
Tue Sep 12, L7: Object Detection II
Thu Sep 14, L8: Object Detection III
Tue Sep 17, L9: Segmentation I
Thu Sep 21, L10: Segmentation II
Tue Sep 26, L11 Segmentation III
Thu Sep 28, L12 Generative Models I
Tue Oct 3, L13: Generative Models II
Thu Oct 5, L14: Generative Models III
Tue Oct 10, No class, Fall Break.
Thu Oct 12 L15 Generative Models IV
Tue Oct 17, L16Β Generative Models Eval & Transformer Intro
Thu Oct 19, L17Β Transformers I
Tue Oct 24, L18 Transformers II
Thu Oct 26, L19 Transformers III
Tue Oct 31, L20 Transformers IV
Thu Nov 2, L21 Diffusion Models I
Tue Nov 7, L22 Diffusion Models II
Thu Nov 9, L23 Diffusion Models III
Tue Nov 14, L24 Light & Color
Thu Nov 16, L25 Filtering & Features
Tue Nov 21 & Thu Nov 23 No class, Thanksgiving Break.
Tue Nov 28, L26 Transformation & Fitting
Thu Nov 30, L27 Β Geometry & Motion & Wrap up
Assignments and Problem Sets
Assignment 1: Introduction to Numpy, PyTorch and related libraries for beginners (release Aug 28, due Sep 4)
Assignment 2: Classification (release Sep 4, due Sep 20, extended 4 days for everyone due to career fair)
Assignment 3: DetectionΒ (release Sep 21, due Oct 8, extended 3 days for everyone due to covid etc.)
Assignment 4: SegmentationΒ (release Oct 5, due Oct 22)
Assignment 5: GenerationΒ (release Oct 22, due Nov 5)
Problem Set 1: Modern VisionΒ (release Nov 5, due Nov 19)
Problem Set 2: Classical Vision Β (release Nov 19, due Nov 30)
Assignment 6 - Extra Credit: Image Stitching.Β (release before Nov 14, due Nov 30)
Note:
Assignment 1-5 is 16 pts each, Assignment 6 is extra credit for up to 10 pts, and problem sets are 10 pts each.
Final Grades: A: 90%+, B: 80%+, C: 70%+, D: 60%+, F<60%.
Late submissions:
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. 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. There is no grace period for project handins. 5 minutes after the deadline is a full day late.Β
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. 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.
TA Contacts:
Manushree: mvasu6@gatech.edu (co-head TA)
Aditya: adityakane@gatech.edu (co-head TA)Β
Kristen: kpereira6@gatech.eduΒ
Dipanwitha: dguhathakurta3@gatech.eduΒ
Arvind: arvind.ramesh@gatech.eduΒ
Dhruv: dpatel756@gatech.eduΒ
Atharva: amete7@gatech.eduΒ
Shubham: smaheshwari44@gatech.eduΒ
TA Office Hours:
Mon 1 to 3:30 pm: Arvind, Dhruv
Tue 9 to 11 am: Manushree, Aditya
Wed 1:30 to 4 pm: Atharva, Dipa
Thur 9 to 11 am: Kristen, Shubham
Location KLAUS 2nd Floor Atrium.Β