Об этом курсе: Deep learning added a huge boost to the already rapidly developing field of computer vision. With deep learning, a lot of new applications of computer vision techniques have been introduced and are now becoming parts of our everyday lives. These include face recognition and indexing, photo stylization or machine vision in self-driving cars. The goal of this course is to introduce students to computer vision, starting from basics and then turning to more modern deep learning models. We will cover both image and video recognition, including image classification and annotation, object recognition and image search, various object detection techniques, motion estimation, object tracking in video, human action recognition, and finally image stylization, editing and new image generation. In course project, students will learn how to build face recognition and manipulation system to understand the internal mechanics of this technology, probably the most renown and oftenly demonstrated in movies and TV-shows example of computer vision and AI.
Для кого этот курс: The course is designed for people (1) who already know the basics of machine learning and deep learning (2) who have never studied image processing and computer vision and want to fill that gap (3) who want to learn how to solve computer vision problems with deep learning.
Автор: National Research University Higher School of Economics
Преподаватели: Anton Konushin, Senior Lecturer
HSE Faculty of Computer Science
Преподаватели: Alexey Artemov, Senior Lecturer
HSE Faculty of Computer Science
| Основные сведения | Course 5 of 7 in the Advanced Machine Learning Specialization |
| Уровень | Advanced |
| Выполнение | 5 weeks of study |
| Язык | English |
| Как пройти курс | Чтобы пройти курс, выполните все оцениваемые задания. |
Программа курса
НЕДЕЛЯ 1
Introduction to image processing and computer vision
Welcome to the "Deep Learning for Computer Vision“ course! In the first introductory week, you'll learn about the purpose of computer vision, digital images, and operations that can be applied to them, like brightness and contrast correction, convolution and linear filtering. These simple image processing methods solve as building blocks for all the deep learning employed in the field of computer vision. Let’s get started!
8 видео
- Видео: Digital images
- Видео: Structure of human eye and vision
- Видео: Color models
- Видео: Image processing goals and tasks
- Видео: Contrast and brightness correction
- Видео: Image convolution
- Видео: Edge detection
Оцениваемый: Basic image processing
Оцениваемый: Image Alignment Notebook
НЕДЕЛЯ 2
Convolutional features for visual recognition
Module two revolves around general principles underlying modern computer vision architectures based on deep convolutional neural networks. We’ll build and analyse convolutional architectures tailored for a number of conventional problems in vision: image categorisation, fine-grained recognition, content-based retrieval, and various aspect of face recognition. On the practical side, you’ll learn how to build your own key-points detector using a deep regression CNN.
12 видео
- Видео: AlexNet, VGG and Inception architectures
- Видео: ResNet and beyond
- Видео: Fine-grained image recognition
- Видео: Detection and classification of facial attributes
- Видео: Content-based image retrieval
- Видео: Computing semantic image embeddings using convolutional neural networks
- Видео: Employing indexing structures for efficient retrieval of semantic neighbors
- Видео: Face verification
- Видео: The re-identification problem in computer vision
- Видео: Facial keypoints regression
- Видео: CNN for keypoints regression
Оцениваемый: Convolutional features for visual recognition
Оцениваемый: Facial keypoints notebook
НЕДЕЛЯ 3
Object detection
In this week, we focus on the object detection task — one of the central problems in vision. We start with recalling the conventional sliding window + classifier approach culminating in Viola-Jones detector. Tracing the development of deep convolutional detectors up until recent days, we consider R-CNN and single shot detector models. Practice includes training a face detection model using a deep convolutional neural network.
13 видео
- Видео: Sliding windows
- Видео: HOG-based detector
- Видео: Detector training
- Видео: Viola-Jones face detector
- Видео: Attentional cascades and neural networks
- Видео: Region-based convolutional neural network
- Видео: From R-CNN to Fast R-CNN
- Видео: Faster R-CNN
- Видео: Region-based fully-convolutional network
- Видео: Single shot detectors
- Видео: Speed vs. accuracy tradeoff
- Видео: Fun with pedestrian detectors
Оцениваемый: Object Detection
Оцениваемый: Face detection notebook
НЕДЕЛЯ 4
Object tracking and action recognition
The fourth module of our course focuses on video analysis and includes material on optical flow estimation, visual object tracking, and action recognition. Motion is a central topic in video analysis, opening many possibilities for end-to-end learning of action patterns and object signatures. You will learn to design computer vision architectures for video analysis including visual trackers and action recognition models.
11 видео
- Видео: Optical flow
- Видео: Deep learning in optical flow estimation
- Видео: Visual object tracking
- Видео: Examples of visual object tracking methods
- Видео: Multiple object tracking
- Видео: Examples of multiple object tracking methods
- Видео: Introduction to action recognition
- Видео: Action classification
- Видео: Action classification with convolutional neural networks
- Видео: Action localization
Оцениваемый: Video Analysis
Оцениваемый: Face recognition notebook
НЕДЕЛЯ 5
Image segmentation and synthesis
In the last module of this course, we shall consider problems where the goal is to predict entire image. These are semantic image segmentation and image synthesis problems. Modern CNNs tailored for segmentation employ multiple specialised layers to allow for efficient training and inference. Lastly, we will get to know Generative Adversarial Networks — a bright new idea in machine learning, allowing to generate arbitrary realistic images.
7 видео
- Видео: Oversegmentation
- Видео: Deep learning models for image segmentation
- Видео: Human pose estimation as image segmentation
- Видео: Style transfer
- Видео: Generative adversarial networks
- Видео: Image transformation with neural networks
Оцениваемый: Image segmentation and synthesis
Оцениваемый: GAN notebook
Часто задаваемые вопросы
Как это работает
课程作业
每门课程都像是一本互动的教科书，具有预先录制的视频、测验和项目。
来自同学的帮助
与其他成千上万的学生相联系，对想法进行辩论，讨论课程材料，并寻求帮助来掌握概念。
证书
获得正式认证的作业，并与朋友、同事和雇主分享您的成功。
Авторы
National Research University Higher School of Economics
National Research University - Higher School of Economics (HSE) is one of the top research universities in Russia. Established in 1992 to promote new research and teaching in economics and related disciplines, it now offers programs at all levels of university education across an extraordinary range of fields of study including business, sociology, cultural studies, philosophy, political science, international relations, law, Asian studies, media and communications, IT, mathematics, engineering, and more.
Learn more on www.hse.ru
Стоимость
| Приобрести курс | |
|---|---|
| Получить доступ к материалам курса | Доступен |
| Получить доступ к оцениваемым материалам курса | Доступен |
| Получить итоговую оценку | Доступен |
| Earn a shareable Course Certificate | Доступен |
Рейтинги и отзывы
Coursera делает лучшее в мире образование доступным каждому, предлагая онлайн-курсы от ведущих университетов и организаций.
© Coursera Inc., 2018 Все права защищены.
