VITA

Fall 21 - Advanced Topics in Computer Vision (ECE 381V/CS 395T)

Term

Fall 2021

Meeting times and location

MW 1:30-3:00pm (EER 1.518)

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 and TA Information

Instructor Name

Dr. Zhangyang (Atlas) Wang

Telephone number

512-471-1866

Email address

atlaswang@utexas.edu

Office location

EER 6.886

TA Info:

Xiaohan Chen, xiaohan.chen@utexas.edu

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:

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).

Grading Policies

Grading will be based on class participation (10%), one mid-term exam (30%), and one final project (60%) (middle-term progress report 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

8/25 Wednesday

Introduction and Computer Vision Basics Slides

8/30 Monday

Deep Learning Basics (1): Building A Deep Network

9/01 Wednesday

Deep Learning Basics (2): Representative Models and Tasks

9/03 Monday

- Class Cancelled (Labor Day) -

9/08 Wednesday

Deep Learning Basics (3): Advanced Models and Optimization Slides

9/13 Monday

Topic I: Label-Efficient Learning (1): Semi-Supervised Learning

9/15 Wednesday

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

9/20 Monday

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

9/22 Wednesday

Topic II: Resource-Efficient Learning (1): Basic Model Compression

9/27 Monday

Topic II: Resource-Efficient Learning (2): Advanced Model Compression

9/29 Wednesday

Topic II: Resource-Efficient Learning (3): Efficient Training and Fine-Tuning Slides

10/04 Monday

Topic III: Robust Vision (1): Image Enhancement

10/06 Wednesday

Topic III: Robust Vision (2): Uncertainty

10/11 Monday

Topic III: Robust Vision (3): Domain Generalization

10/13 Wednesday

Topic III: Robust Vision (4): Adversarial Robustness

10/18 Monday

Topic III: Robust Vision (5): Synthetic Data Slides

10/20 Wednesday

Topic IV: Generative Models (1)

10/25 Monday

Topic IV: Generative Models (2)

10/27 Wednesday

Topic IV: Generative Models (3) Slides

11/01 Monday

Topic V: AutoML and Meta Learning (1)

11/03 Wednesday

Topic V: AutoML and Meta Learning (2)

11/08 Monday

Topic V: AutoML and Meta Learning (3) Slides

11/10 Wednesday

Topic VI: Vision and Language (1)

11/15 Monday

Topic VI: Vision and Language (2) Slides

11/17 Wednesday

Topic VII: Transformers and MLPs in Vision (1)

11/22 Monday

Topic VII: Transformers and MLPs in Vision (2)

11/24 Wednesday

- Class Cancelled (Thanksgiving Vacation) -

11/29 Monday

Topic VII: Transformers and MLPs in Vision (3) Slides

12/01 Wednesday

Class Project Presentation (1)

12/06 Monday

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, UIUC, UC Berkeley, GaTech, UVa, Microsoft, DeepMind, NVIDIA, and more. The instructor owes many thanks for their generosity of sharing those materials publicly.