VITA

Spring 23 - Advanced Topics in Computer Vision (ECE 381V/CS 395T)

Course title

ECE 381V/CS 395T: Advanced Topics in Computer Vision

Term

Spring 2023

Meeting times and location

MW 10:30am -12:00pm (BUR 130)

After-class platform

Slack (link sent to registered students)

Video recording

Available

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

atlaswang@utexas.edu

Office hour time

Tuesday 10:00am - 11:00am

Office hour location

EER 6.886 (instructor office)

TA Information

TA Name

Xinyu Gong

Email address

xinyu.gong@utexas.edu

Office hour time

Thursday 4:00pm - 5:00pm

Office hour location

EER 3.854

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 (20%), and one final project (70%) (middle-term progress report 15% + presentation 20% + final report 20% + 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

1/09 Monday

Topic I: Deep Vision Backbones (1): Building Blocks

1/11 Wednesday

Topic I: Deep Vision Backbones (2): Convolutional Neural Networks

1/16 Monday

- No Class (Martin Luther King, Jr. Day) -

1/18 Wednesday

Topic I: Deep Vision Backbones (3): More Advanced Architectures

1/23 Monday

Topic I: Deep Vision Backbones (4): Vision Transformers Slides

1/25 Wednesday

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

1/30 Monday

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

2/01 Wednesday

Topic II: Label-Efficient Learning (3): Transfer & Self-Supervised Learning Slides

2/06 Monday

Topic III: Resource-Efficient Learning (1): Model Compression

2/08 Wednesday

Topic III: Resource-Efficient Learning (2): Efficient Training and Fine-Tuning

2/13 Monday

Topic III: Resource-Efficient Learning (3): Advanced Sparsity, and Mixture-of-Experts Slides

2/15 Wednesday

Topic IV: Robust Vision (1): Image Enhancement

2/20 Monday

Topic IV: Robust Vision (2): Uncertainty

2/22 Wednesday

Topic IV: Robust Vision (3): Domain Generalization

2/27 Monday

Topic IV: Robust Vision (4): Adversarial Robustnes Slides

3/01 Wednesday

Topic V: AutoML and Meta Learning (1)

3/06 Monday

Topic V: AutoML and Meta Learning (2)

3/08 Wednesday

Topic V: AutoML and Meta Learning (3) Slides

3/13 Monday

- No Class (Spring Break) -

3/15 Wednesday

- No Class (Spring Break) -

3/20 Monday

Topic VI: Generative Adversarial Networks (1)

3/22 Wednesday

Topic VI: Generative Adversarial Networks (2)

3/27 Monday

Topic VI: Generative Adversarial Networks (3) Slides

3/29 Wednesday

Topic VII: Neural Radiance Fields (1): Single Scene Fitting

4/03 Monday

Topic VII: Neural Radiance Fields (2): Cross-Scene Fitting [guest lecture]

4/05 Wednesday

Topic VII: Neural Radiance Fields (3): Beyond NeRFs [guest lecture] Slides

4/10 Monday

Topic VIII: Vision and Language (1): Image to Text (image captioning, VQA)

4/12 Wednesday

Topic VIII: Vision and Language (2): Introduction to Diffusion Models (the game changer!)

4/17 Monday

Topic VIII: Vision and Language (3): Text to Image: Stable Diffusion and the "AIGC" trend Slides

4/19 Wednesday

Class Project Presentation (1)

4/24 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, 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.