Fall 21 - Advanced Topics in Computer Vision (ECE 381V/CS 395T)
Term:​
Fall 2021
Meeting times and location:
MW 1:30pm -3:00pm (ECJ 1.318)
Course Description and Prerequisites
This is a research-oriented advanced class that intends to focus on the latest frontier of computer vision. It describes computer vision algorithms that make sense of photographs, video, and other imagery. Applications include robotics, content creation, entertainment, medical image analysis, smart home, security, and HCI, among many others. Through this course, the students will digest and practice their knowledge and skills by many open discussions in classes, and will obtain in-depth experience with a particular research topic through a final project.
Students should have taken the following courses or equivalent: Introduction to Computer Vision (379K), Convex Optimization (381K-18), and Probability & Stochastic Process I (381J).
Previous knowledge of the following courses is helpful, but not necessary: Digital Video (381K-16), Statistical Machine Learning (381V), Data Mining (381L-10), or Cross-Layer Machine Learning HW/SW Design (382V).
Coding experiences with Python are necessary and assumed. Previous knowledge of C/C++, MATLAB or Tensorflow is very helpful, but not necessary.
Instructor Information
Instructor Name:
Dr. Zhangyang (Atlas) Wang
Telephone number:
512-471-1866
Email address:
Office location:
EER 6.886
TA Info:
Zoom and Slack Links:
sent to registered students
Textbook and/or Resource Material
This course does not follow any textbook closely. Among many recommended readings are:
Grading Policies
Grading will be based on class participation (10%), one mid-term exam (15%), and one final project (75%) (milestone 1 progress report 15% + milestone 2 progress report 15% + presentation 20% + final report 15% + code review 10%). There will be no final exam.
Course Topics
8/25 Wednesday
8/30 Monday
9/01 Wednesday
​
9/03 Monday
​
9/08 Wednesday
​
9/13 Monday
9/15 Wednesday
9/20 Monday
9/22 Wednesday
9/27 Monday
​
9/29 Wednesday
​
10/04 Monday
10/06 Wednesday
​
10/11 Monday
​
10/13 Wednesday
​
10/18 Monday
10/20 Wednesday
10/25 Monday
10/27 Wednesday
11/01 Monday
11/03 Wednesday
11/08 Monday
11/10 Wednesday
11/15 Monday
11/17 Wednesday
11/22 Monday
11/24 Wednesday
​
11/29 Monday
12/01 Wednesday
12/06 Monday
​
-
Pattern Recognition and Machine Learning, Christopher M. Bishop (2006).
-
Computer Vision: Algorithms and Applications, Richard Szeliski (2010).
-
Deep Learning, Ian Goodfellow, Yoshua Bengio and Aaron Courville (2016).
-
Diving into Deep Learning, Aston Zhang, Zack Lipton, Mu Li and Alex Smola (2019).
-
One project to receive the Best Project Award, voted by all class members. (+5%)
-
Projects in the novel, interdisciplinary domains (some examples: 5G/6G telecommunication, brain-computer interface, economics & markets, COVID-19, etc.), judged by the instructor. (+2%)
-
For late submission, each additional late day will incur a 10% penalty.
Introduction and Computer Vision Basics Slides
Deep Learning Basics (1): Building A Deep Network
​
Deep Learning Basics (2): Representative Models and Tasks
​
- Class Cancelled (Labor Day) -
​​
Deep Learning Basics (3): Advanced Models and Optimization Slides
​
Topic I: Label-Efficient Learning (1): Semi-Supervised Learning
​
Topic I: Label-Efficient Learning (2): Few-Shot & Active Learning
​
Topic I: Label-Efficient Learning (3): Transfer & Multi-Task & Self-Supervised Learning Slides
​
Topic II: Resource-Efficient Learning (1): Basic Model Compression
​
Topic II: Resource-Efficient Learning (2): Advanced Model Compression
​
Topic II: Resource-Efficient Learning (3): Efficient Training and Fine-Tuning Slides
​
Topic III: Robust Vision (1): Image Enhancement
​
Topic III: Robust Vision (2): Uncertainty
​
Topic III: Robust Vision (3): Domain Generalization
​
Topic III: Robust Vision (4): Adversarial Robustness
​
Topic III: Robust Vision (5): Synthetic Data Slides
​
Topic IV: Generative Models (1)
​
Topic IV: Generative Models (2)
​
Topic IV: Generative Models (3) Slides
​
Topic V: AutoML and Meta Learning (1)
​
Topic V: AutoML and Meta Learning (2)
​
Topic V: AutoML and Meta Learning (3) Slides
​
Topic VI: Vision and Language (1)
​
Topic VI: Vision and Language (2) Slides
​
Topic VII: Transformers and MLPs in Vision (1)
​
Topic VII: Transformers and MLPs in Vision (2)
​
- Class Cancelled (Thanksgiving Vacation) -
​
Topic VII: Transformers and MLPs in Vision (3) Slides
​
Class Project Presentation (1)
​
Class Project Presentation (2)
​
Acknowledgement
Many materials included in this course are adapted from the existing teaching or tutorial slides, created by colleagues in CMU, Stanford, UIUC, UC Berkeley, GaTech, Microsoft, Google, Meta, DeepMind, NVIDIA, and more. The instructor owes many thanks for their generosity of sharing those materials publicly.