Project seminar "Deep learning for computer vision"

2023/2024

Учебный год

ENG

Обучение ведется на английском языке

9

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

Преподаватели

Булычев Иван Даниилович

Рассадин Александр Георгиевич

Course Syllabus

Abstract

This course covers basics of Deep Learning approaches applied to the popular Computer Vision tasks. The aim of the course is to highlight how the modern 2D Computer Vision works and how the area evolved to this. Students will learn the main concepts of the modern 2D Computer Vision, how to master some popular applied tasks and try by themselves. Every week, the students will learn a standalone chapter of Computer Vision starting from the Image Classification approaches, through Object Detection, Image Segmentation and ending with some cutting-edge and real-life approaches. The students also will introduced to the popular datasets for each task along with the common quality estimation procedures and open source solutions.

Learning Objectives

• Students will learn how to use pretrained image classifiers and build their own
• Students will touch with modern Deep Learning frameworks
• Students will build their first neural networks models

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

• test
• test2
• EXAM

Interim Assessment

• 2023/2024 4th module
  0.5 * EXAM + 0.5 * test + 0 * test2

Bibliography

Recommended Core Bibliography

• Introduction to deep learning, Charniak, E., 2018

Recommended Additional Bibliography

• Deep learning, Kelleher, J. D., 2019
• Image analysis, classification, and change detection in remote sensing : with algorithms for Python, Canty, M. J., 2019

Authors

• Лабанина Алина Валерьевна