BMI 826 / CS 838 Learning Based Methods in Computer Vision

Spring 2019, MW 1:05PM - 2:20PM, 3534 Engineering Hall
Instructor: Yin Li

TA: Zixuan Huang

Computer Vision, art by kirkh.deviantart.com

Course Description

The course focuses on the problems of representation and reasoning for large amounts of visual data. These data include images and videos, medical imaging data and their associated tags or text. The majority of these problems stems from computer vision and machine learning. The content of the course is organized into two main sections. The first section introduces deep learning in the context of computer vision, including its theory, models, practice and systems. In the second part, we will cover topics on visual recognition, such as image classification, object detection, human pose estimation, action recognition, 3D understanding and medical image recognition.

Discussion Group

We will use Piazza. Please post all of your questions on the discussion board so that others may learn from your questions as well. Do not email the professor or TA directly with homework questions.

Prerequisites

Students are strongly encouraged to have knowledge of computer vision (CS 766) or medical image analysis (BMI/CS 767). No prior experience with machine learning is assumed, although previous knowledge of basic machine learning concepts will be helpful. The following skills are necessary for this class:

Grading

Your final grade will be made up from Most of the assignments and projects are team based. And we do not allow late homework assignments or projects. However, you have three "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.

These late days are intended to cover unexpected clustering of due dates, travel commitments, interviews, hackathons, etc. Don't ask for extensions to due dates because we are already giving you a pool of late days to manage yourself.

Homework Assignments

The course will consist of 3 homework assignments. The second and third assignments are team based. Teams of 2 students are strongly preferred. In your submission, please clearly identify the contribution of all the team members. Please note that members in the same group will not necessarily get the same grade.

Please post all of your questions on Piazza so that others may learn from your questions as well. Do not email the professor or TA directly with homework questions.

All homeworks are to be submitted by midnight on the due date. Include all the files in a zip file named hwX_yourNetID.zip (where X is the homework number) and upload the zip file to Canvas. Late submissions should be emailed to the TA (and carbon the instructor). Please attach the zip file in your email.

All starter code and assignments will be in Python with the use of various third party libraries. We will make an effort to support MacOS, Windows, and Linux. The course includes a quick python tutorial (optional) and assumes you have enough familiarity with procedural and object-oriented programming languages to complete the projects.

Projects

The final project is research-oriented. It can be a pure vision project or an application of vision technique in the student's own research area. You are expected to implement one (or more) related research papers, or think of some interesting novel ideas and implement them using the techniques discussed in class. Students are encouraged to propose their own project topics. You should work on the project in groups of 2-3. In your submission, please clearly identify the contribution of both group members.

There will be four checkpoints: a project proposal, an intermediate milestone report, a final project report and a project presentation. The details are listed below.

Academic Integrity

This course follows the University of Wisconsin-Madison Code of Academic Integrity. Unless specifically authorized by the instructor, all coursework is to be done by the student working alone. Violations of the rules will not be tolerated.

You are permitted and encouraged to discuss ideas with other students. However, you are expected to implement the core components of each assignment / project on your own. You should not view or edit anyone else's code. You should not post code to Piazza, except for starter code / helper code that isn't related to the core project.

Contact Info and Office Hours

If possible, please use Piazza to ask questions and seek clarifications before emailing the instructor or TA. Office Hours

Syllabus

Class Date Topic Slide Reading Assignment
Computer Vision Meets Machine Learning
Wed, Jan 23 No Class, Instructor Travel
Mon, Jan 28 Introduction to Visual Recognition
(Guest Lecture by Prof. Vikas Singh)
See Canvas Sign up for Piazza
Wed, Jan 30 Class Cancelled, Campus Partial Closure
Mon, Feb 4 Image Processing in Python
Tutorial led by the TA
Homework 1 out
Wed, Feb 6 Data Driven Paradigm
(Guest Lecture by Prof. Yingyu Liang)
Paper 1, 2
Mon, Feb 11 No Class, Instructor Travel
Deep Models for Visual Learning
Wed, Feb 13 Introduction to Deep Learning Systems
(PyTorch/TensorFlow) Led by the TA
Mon, Feb 18 No Class, Instructor Travel Homework 1 due
Wed, Feb 20 Introduction to Computational Cameras
(Guest Lecture by Prof. Mohit Gupta)
Paper
Mon, Feb 25 Introduction to Neural Networks
Wed, Feb 27 Convolutional Neural Networks: Theory
Mon, Mar 4 Convolutional Neural Networks: Practice Paper 1, 2, 3
Wed, Mar 6 Recurrent Neural Networks Reading Quiz 1
Visual Recognition
Mon, Mar 11 Image Classification Paper Project proposal due
Homework 2 out
Wed, Mar 13 Object Detection: Part I Paper 1, 2
Mon, Mar 18 No class, Spring Recess
Wed, Mar 20 No class, Spring Recess
Mon, Mar 25 Object Detection: Part II Paper 1, 2
Wed, Mar 27 Semantic Segmentation Paper 1, 2
Mon, Apr 1 Human Pose Estimation Paper 1, 2 Homework 2 due
Wed, Apr 3 Beyond Classification: Vision & Language Paper 1, 2
Mon, Apr 8 Action Recognition Paper 1, 2 Project mid-term report due
Wed, Apr 10 3D Scene Understanding Paper 1, 2
Mon, Apr 15 Deep Generative Models: Part I Paper 1, 2 Homework 3 out
Wed, Apr 17 Deep Generative Models: Part II Paper 1, 2
Fri, Apr 19 Introduction to Visual Perception
Mon, Apr 22 Medical Image Recognition
Wed, Apr 24 Weak Supervision, Self Supervision and
Learning from Simulation
Quiz 2
Project Presentations
Mon, Apr 29 Project Presentations Homework 3 due
Wed, May 1 Project Presentations
Fri, May 3 Project Presentations and Course Wrap-up Project report due
Final Exam Period - not used

Acknowledgments

The materials from this class rely significantly on slides prepared by other instructors, especially many slides are modified from those of Abhinav Gupta, Svetlana Lazebnik and Alexei A. Efros, who in turn uses materials from many people. Each slide set contains acknowledgments. Feel free to use these slides for academic or research purposes, but please maintain all acknowledgments.