Course title
EE 381V: Advanced Topics in Computer Vision

Spring 2021

Meeting times and location
MW 5:00-6:30pm (online)

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: 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

Dr. Zhangyang (Atlas) Wang

Telephone number

Email address

Office location
EER 6.886

Zoom Link
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%), three in-class quizzes (10% each), and one final project (60%) (proposal 15% + presentation 15% + final report 15% + code review 15%). There will be no final exam.

  • 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.
Course Topics

1/20 Wednesday
Introduction and Computer Vision Basics Slides

1/25 Monday
Deep Learning Basics (1): Building A Deep Network

1/27 Wednesday
Deep Learning Basics (2): Representative Models and Tasks

2/01 Monday
Deep Learning Basics (3): Advanced Models and Optimization Slides

2/03 Wednesday
Topic I: Label-Efficient Learning (1): Semi-Supervised Learning

2/08 Monday
Topic I: Label-Efficient Learning (2): Few-Shot & Active Learning

2/10 Wednesday
Topic I: Label-Efficient Learning (3): Transfer & Multi-Task & Self-Supervised Learning Slides

2/15 Monday
- Class Cancelled (winter storm) -

2/17 Wednesday
- Class Cancelled (winter storm) -

2/22 Monday
Topic II: Resource-Efficient Learning (1): Model Compression

2/24 Wednesday
Topic II: Resource-Efficient Learning (2): Efficient Training Slides

3/01 Monday
Topic III: Robust Vision (1): Image Enhancement

3/03 Wednesday
Topic III: Robust Vision (2): Uncertainty

3/08 Monday
Topic III: Robust Vision (3): Domain Generalization

3/10 Wednesday
Topic III: Robust Vision (4): Adversarial Robustness Slides

3/22 Monday
Topic IV: Generative Models - GANs and VAEs (1)

3/24 Wednesday
Topic IV: Generative Models - GANs and VAEs (2)

3/29 Monday
Topic IV: Generative Models - GANs and VAEs (3)Slides

3/31 Wednesday
Topic V: AutoML and Meta Learning (1)

4/05 Monday
Topic V: AutoML and Meta Learning (2)

4/07 Wednesday
Topic V: AutoML and Meta Learning (3)Slides

4/12 Monday
Topic VI: Vision and Language (1)

4/14 Wednesday
Topic VI: Vision and Language (2)

4/19 Monday
Topic VI: Vision and Language (3)Slides

4/21 Wednesday
Special Topics (1): Scaling up Vision with Synthetic Data Slides

4/26 Monday
Special Topics (2): Visual TransformersSlides

4/28 Wednesday
Special Topics (3): Ethics and Privacy in Computer VisionSlides

5/03 Monday
Class Project Presentation (1)

5/05 Wednesday
Class Project Presentation (2)


Many materials included in this course are adapted from the existing teaching or tutorial slides, created by colleagues in CMU, UIUC, UC Berkeley, GaTech, UVa, Microsoft, DeepMind, NVIDIA, and more. The instructor owes many thanks for their generosity of sharing those materials publicly.