CS827 - Deep Learning in Visual Computing Applications
| TIMETABLE | TEACHING MATERIAL |
| Credits | 10 |
| Level | 5 |
| Semester | Semester 2 |
| Availability | Deep Learning in Visual Computing Applications |
| Prerequisites | CS826 - Deep Learning Theory and Practice |
| Learning Activities Breakdown | Lectures: 10 hours | Practical/Labs: 10 hours Homework / Private Study: 80 |
| Assessment | One individual assignment worth 100% |
| Lecturer | Feng Dong |
Aims and Objectives
The aim of this module is to endow students with:
- an understanding of the key algorithms and techniques with deep learning in visual computing.
- an understanding of the limitations of the current technologies and their future trend.
Learning Outcomes
After completing this module participants will be able to:
- understand convolutional neural networks and their learned feature maps.
- understand techniques of object detection and segmentation from images.
- understand applications of conditional generative models in visual computing.
Syllabus
- Review of Convolutional Neural Networks (CNN).
- Visualization of CNN features and model explainability.
- Object detection from images with region proposal network and faster r-cnn.
- Image segmentation with deep neural network.
- Image generation with generative models (e.g. image super-resolution or style transfer).
Recommended Reading
This list is indicative only – the class lecturer may recommend alternative reading material. Please do not purchase any of the reading material listed below until you have confirmed with the class lecturer that it will be used for this class.
Practical Machine Learning and Image Processing: For Facial Recognition, Object Detection, and Pattern Recognition Using Python. Singh, H.
Last updated: 2022-09-09 13:43:39