Deep learning for computer vision

2021/2022

Учебный год

ENG

Обучение ведется на английском языке

7

Кредиты

Кто читает:

Кафедра прикладной математики и информатики (Нижний Новгород) (Факультет информатики, математики и компьютерных наук (Нижний Новгород))

Статус:

Курс обязательный

Когда читается:

1-й курс, 4 модуль

Преподаватель

Рассадин Александр Георгиевич

Course Syllabus

Abstract

This course covers basics of Deep Learning approaches applied to the popular Computer Vision tasks. Students will learn the main concepts of the modern 2D Computer Vision, how to master some popular applied tasks and try by themselves.

Learning Objectives

• The aim of the course is to highlight how the modern 2D Computer Vision works and how the area evolved to this.

Expected Learning Outcomes

• Students will touch with modern Deep Learning frameworks
• Students will build their first neural networks model
• Students will learn how to use pretrained image classifiers and build their own
• Students will learn how to use pretrained object detector and build their own
• Students will learn how to use existing REID models and build their own
• Students will learn how to track their objects
• Students will learn how to use pretrained image segmentation model and build their own
• Students will attempt to create a prototype of real-life video surveillance solution

Course Contents

• Introduction to Deep Learning.
• Deep Learning for Image Classification
• Deep Object Detection
• Deep Object Tracking and Person Reidentification
• Deep Image Segmentation
• Final project

Assessment Elements

• Final project
  Testing assignment (each week): 0.2 Programming Assignment (2 per course): 0.4 Final exam: 0.4 1-2 practical tasks per video without evaluation 2-3 questions per video for self-testing without evaluation
• Testing assignment week 1
  Testing Assignment, Practical (without evaluation) tasks
• Testing Assignment week 2
  Testing Assignment, Practical (without evaluation) tasks
• Testing Assignment week 3
  Testing Assignment, Practical (without evaluation) tasks
• Testing Assignment week 4
  Testing Assignment, Practical (without evaluation) tasks
• Testing Assignment week 5
  Testing Assignment, Practical (without evaluation) tasks
• Programming Assignment
• Programming Assignment

Interim Assessment

• 2021/2022 4th module
  0.2 * Programming Assignment + 0.4 * Final project + 0.04 * Testing Assignment week 5 + 0.2 * Programming Assignment + 0.04 * Testing Assignment week 4 + 0.04 * Testing Assignment week 3 + 0.04 * Testing Assignment week 2 + 0.04 * Testing assignment week 1

Bibliography

Recommended Core Bibliography

• Attentional PointNet for 3D-Object Detection in Point Clouds. (2019). Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.EC02C194
• Huang, K., Hussain, A., Wang, Q.-F., & Zhang, R. (2019). Deep Learning: Fundamentals, Theory and Applications. Cham, Switzerland: Springer. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=2029631
• Image analysis, classification, and change detection in remote sensing : with algorithms for Python, Canty, M. J., 2019
• Introduction to deep learning, Charniak, E., 2018

Recommended Additional Bibliography

• Deep learning, Kelleher, J. D., 2019
• Jiao, L., Zhang, F., Liu, F., Yang, S., Li, L., Feng, Z., & Qu, R. (2019). A Survey of Deep Learning-based Object Detection. https://doi.org/10.1109/ACCESS.2019.2939201