Get updates on Eligibility, Admission, Placements Fees Structure
Quick Facts
| Medium Of Instructions | Mode Of Learning | Mode Of Delivery |
|---|---|---|
| English | Self Study | Video and Text Based |
Course Overview
The Deep Learning in Computer Vision online course by Coursera is focused on introducing learners to computer vision, right from the basics. Eventually, the certification course moves to deep learning models which are more modern. Image, as well as video recognition, is a primary part of the programme. The comprehensive curriculum will cover image annotation and classification, motion estimation, human action recognition, and more.
Moreover, Deep Learning in Computer Vision programme is the fifth course in the Advanced Machine Learning Specialization. The National Research University Higher School of Economics offers an online course in association with Coursera. The Deep Learning in Computer Vision certification course is an advanced-level course with a self-paced learning option. You will also work on a final project to implement their learnings.
In the course project for the Deep Learning in Computer Vision course, you will learn to build face recognition and manipulation systems. This project will help you get an idea about the internal mechanics of this technology. The online course also includes a shareable certificate which you will receive from Coursera upon successful completion.
The Highlights
Shareable certificate
Flexible deadlines
Self-paced training
100% online
Financial aid available
Advanced-level course
Peer feedback
Final project
Discussion board
Programme Offerings
- Graded Assignments
- Hands on project
- Shareable Certificate
- Flexible Deadlines
- Course completion certificate
- advanced level course
- Discussion Board
Courses and Certificate Fees
| Certificate Availability | Certificate Providing Authority |
|---|---|
| yes | Coursera |
The fee structure for the course is provided in the table below:
Deep Learning in Computer Vision fee structure
Enrollment Option | Fee (monthly) |
Advanced Machine Learning Specialization | Rs 3,686 |
Eligibility Criteria
To get a certificate, candidates have to complete all the modules and assignments. In addition, they also have to get the minimum passing marks. When students fulfil these requirements, they will get a course completion certificate from Coursera, which can be attached to the LinkedIn page or resume.
What you will learn
Once you finish the Deep Learning in Computer Vision online course, you will become proficient in the following:
Image and video recognition
Image search and object recognition, video, and image recognition
Different types of human action techniques object tracking in video, motion estimation, human action recognition
Lastly, stylization of image, new image generation and editing
Who it is for
Admission Details
You can join the Deep Learning in Computer Vision programme by following the steps mentioned below:
Step 1. Visit the Course page.
Step 2. Look for “Deep Learning in Computer Vision” in the catalogue of Coursera. Click on the information page of the course.
Step3. Choose the ‘Enrol for free’ option.
Step 4. Follow the instructions to enrol in the course.
Step 5. Make the fee payment if you are interested in subscribing to the specialisation course and get easy access to all course materials. After you finish the enrolment process, you can begin the online course.
Application Details
To join the Deep Learning in Computer Vision course, share your name and email. Enter a password to finish your login process. Start the course once the enrollment process is complete. You can sign in with your Coursera/Google/Facebook ID. first-time users also get a seven-day free trial.
The Syllabus
- About University
- Digital images
- Image processing- goals and tasks
- A short introduction to computer vision
- Image convolution
- Structure of the human eye and vision
- Edge detection
- Colour models
- Brightness correction and contrast
- Image Classification recap
- Fine-grained image recognition
- AlexNet, VGG, and Inception architectures
- ResNet and beyond
- Compute semantic image embeddings with convolutional neural networks
- Face verification
- Detection and classification of facial attributes
- Re-identification problem in computer vision
- Facial keypoints regression
- Content-based image retrieval
- Employ indexing structures for efficient retrieval of semantic neighbours
- CNN for key points regression
- Attentional cascades and neural networks
- Object detection problem
- Detector training
- Sliding windows
- HOG-based detector
- Viola-Jones face detector
- Right from R-CNN to Fast R-CNN
- Region-based fully-convolutional network
- Region-based convolutional neural network
- Faster R-CNN
- Single-shot detectors
- Fun with pedestrian detectors
- Speed vs. accuracy tradeoff
- Video Analysis - Introduction
- Visual object tracking
- Examples- visual object tracking methods
- Optical flow
- Introduction to action recognition
- Deep learning in optical flow estimation
- Action localization
- Multiple object tracking
- Examples- multiple object tracking methods
- Action classification
- Action classification with convolutional neural networks
- Over-segmentation
- Image segmentation
- Deep learning models for image segmentation
- Style transfer
- Human pose estimation as image segmentation
- Image transformation using neural networks
- Generative adversarial network
HSE University Frequently Asked Questions (FAQ's)
If you face technical problems, you can write your queries to coursera@hse.ru.
You can either opt for an audit, wherein you can view the syllabus and course materials for free.
The Deep Learning in Computer Vision course has modules spread out over five weeks. Candidates will need 13 hours to complete the course.
The Deep Learning in Computer Vision certification course is an advanced-level course.
The online course is flexible and completed according to the convenience of the students. The course also enables students to reset deadlines, complete assignments, and listen to lectures at your own pace.