关于此课程： 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.
此课程适用人群： 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.
制作方： National Research University Higher School of Economics
教学方： Anton Konushin, Senior Lecturer
HSE Faculty of Computer Science
教学方： Alexey Artemov, Senior Lecturer
HSE Faculty of Computer Science
| 基本信息 | 课程 5（共 7 门，Advanced Machine Learning Specialization ） |
| 级别 | 高级设置 |
| 承诺学习时间 | 5 weeks of study |
| 语言 | English |
| 如何通过 | 通过所有计分作业以完成课程。 |
| 用户评分 |
授课大纲
第 1 周
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 个视频
- 视频: Digital images
- 视频: Structure of human eye and vision
- 视频: Color models
- 视频: Image processing goals and tasks
- 视频: Contrast and brightness correction
- 视频: Image convolution
- 视频: Edge detection
已评分: Basic image processing
已评分: Image Alignment Notebook
第 2 周
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 个视频
- 视频: AlexNet, VGG and Inception architectures
- 视频: ResNet and beyond
- 视频: Fine-grained image recognition
- 视频: Detection and classification of facial attributes
- 视频: Content-based image retrieval
- 视频: Computing semantic image embeddings using convolutional neural networks
- 视频: Employing indexing structures for efficient retrieval of semantic neighbors
- 视频: Face verification
- 视频: The re-identification problem in computer vision
- 视频: Facial keypoints regression
- 视频: CNN for keypoints regression
已评分: Convolutional features for visual recognition
已评分: Facial keypoints notebook
第 3 周
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 个视频
- 视频: Sliding windows
- 视频: HOG-based detector
- 视频: Detector training
- 视频: Viola-Jones face detector
- 视频: Attentional cascades and neural networks
- 视频: Region-based convolutional neural network
- 视频: From R-CNN to Fast R-CNN
- 视频: Faster R-CNN
- 视频: Region-based fully-convolutional network
- 视频: Single shot detectors
- 视频: Speed vs. accuracy tradeoff
- 视频: Fun with pedestrian detectors
已评分: Object Detection
已评分: Face detection notebook
第 4 周
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 个视频
- 视频: Optical flow
- 视频: Deep learning in optical flow estimation
- 视频: Visual object tracking
- 视频: Examples of visual object tracking methods
- 视频: Multiple object tracking
- 视频: Examples of multiple object tracking methods
- 视频: Introduction to action recognition
- 视频: Action classification
- 视频: Action classification with convolutional neural networks
- 视频: Action localization
已评分: Video Analysis
已评分: Face recognition notebook
第 5 周
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 个视频
- 视频: Oversegmentation
- 视频: Deep learning models for image segmentation
- 视频: Human pose estimation as image segmentation
- 视频: Style transfer
- 视频: Generative adversarial networks
- 视频: Image transformation with neural networks
已评分: Image segmentation and synthesis
已评分: GAN notebook
常见问题解答
运作方式
Coursework
Each course is like an interactive textbook, featuring pre-recorded videos, quizzes and projects.
Help from Your Peers
Connect with thousands of other learners and debate ideas, discuss course material, and get help mastering concepts.
Certificates
Earn official recognition for your work, and share your success with friends, colleagues, and employers.
制作方
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
价格
| 购买课程 | |
|---|---|
| 访问课程材料 | 可用 |
| 访问评分的材料 | 可用 |
| 收到最终成绩 | 可用 |
| 获得可共享的课程证书 | 可用 |
评分和审阅
Excellent course! Quiz questions are conceptual and challenging and assignments are pretty rigorous and 100% practical application oriented.
Great content! Great assignments ideas. Problems with graders. Quizes and especially assignments, are loosely related to the lecture materials. The ability of authors to explain things is pretty week (it is not even close to Andrew Ng skills). The efforts necessary to complete assignments are ridiculously underestimated. You will need 10-20 hours or even more for each assignment, instead of 2hr specified. Total experience is very contradictory. I chose between 3 and 4. 3 is too low mark for these unique content, and creative assignment ideas, and I hope the assignment format could be improved in the feature, with not so many efforts (some tips, and intermediate assertions could help a lot). As for now, I could not recommend this course for wide audience, only for the most "desperate" students.