This course introduces modern concepts in computer vision from machine learning perspective. It aims at giving insights into how the computers understand the three-dimensional world from visual data (images and video). The topics to be covered will be on processing, analysis, understanding, and synthesis of images. The course will provide both theoretical/mathematical and practical aspects. The lab hours will be full of hands-on tasks performed by the students.
Prerequisite(s)
Proficiency in programming and familiarity with linear algebra/calculus are required. Some familiarity with machine learning and image processing (at the level of CSE0451) will be a plus. Prior Python experience will also be helpful, but if you’ve never used Python that is not a problem, as long as you have programming experience.
· Ian Goodfellow, Yoshua Bengio, Aaron Courville. Deep Learning. MIT Press. 2016 (available online)
Other Sources
1. Concise Computer Vision: An Introduction into Theory and Algorithms, Springer, Series: Undergraduate Topics in Computer Science, by Reinhard Klette, 2014. ISBN 978-1-4471-6319-0 ;
Course Schedules
Week
Contents
Learning Methods
1. Week
Course Introduction
Oral Presentation, Laboratory
2. Week
Image Classification, Linear Classifiers
Oral Presentation, Laboratory
3. Week
Regularization, Optimization, Neural Networks
Oral Presentation, Laboratory
4. Week
Backpropagation, Convolutional Networks
Oral Presentation, Laboratory
5. Week
CNN Architectures I
Oral Presentation, Laboratory
6. Week
Training Neural Networks
Oral Presentation, Laboratory
7. Week
CNN Architectures II
Oral Presentation, Laboratory
8. Week
Midterm
Oral Presentation, Laboratory
9. Week
Object Detection
Oral Presentation, Laboratory
10. Week
Image Segmentation
Oral Presentation, Laboratory
11. Week
Recurrent Networks
Oral Presentation, Laboratory
12. Week
Attention and Vision Transformers
Oral Presentation, Laboratory
13. Week
Generative Models
Oral Presentation, Laboratory
14. Week
Project Presentations
Oral Presentation, Laboratory
15. Week
16. Week
17. Week
Assessments
Evaluation tools
Quantity
Weight(%)
Midterm(s)
1
30
Project(s)
1
30
Lab Assignments
1
10
Final Exam
1
30
Program Outcomes
PO-1
Adequate knowledge in mathematics, science and engineering subjects pertaining to the relevant discipline; ability to use theoretical and applied information in these areas to model and solve engineering problems.
PO-2
Ability to identify, formulate, and solve complex engineering problems; ability to select and apply proper analysis and modelling methods for this purpose.
PO-3
Ability to design a complex system, process, device or product under realistic constraints and conditions, in such a way so as to meet the desired result; ability to apply modern design methods for this purpose. (Realistic constraints and conditions may include factors such as economic and environmental issues, sustainability, manufacturability, ethics, health, safety issues, and social and political issues according to the nature of the design.)
PO-4
Ability to devise, select, and use modern techniques and tools needed for engineering practice; ability to employ information technologies effectively.
PO-5
Ability to design and conduct experiments, gather data, analyse and interpret results for investigating engineering problems.
PO-6
Ability to work efficiently in intra-disciplinary and multi-disciplinary teams; ability to work individually.
PO-7
Ability to communicate effectively, both orally and in writing; knowledge of a minimum of one foreign language.
PO-8
Recognition of the need for lifelong learning; ability to access information, to follow developments in science and technology, and to continue to educate him/herself.
PO-9
Awareness of professional and ethical responsibility.
PO-10
Information about business life practices such as project management, risk management, and change management; awareness of entrepreneurship, innovation, and sustainable development.
PO-11
Knowledge about contemporary issues and the global and societal effects of engineering practices on health, environment, and safety; awareness of the legal consequences of engineering solutions.
Learning Outcomes
LO-1
1. I have a comprehension on data-driven approaches and know how they are used in image classification.
LO-2
2. I am familiar with the concepts of regularization and optimization.
LO-3
3. I can discuss and compare neural and convolutional networks. I am familiar with various CNN architectures.
LO-4
4. I have a comprehension on data-driven approaches and know how they are used in object detection.
LO-5
5. I have a comprehension on data-driven approaches and know how they are used in image segmentation.
LO-6
6. I am familiar with the foundation of recurrent networks.
LO-7
7. I am familiar with the foundations of attention mechanism, and vision transformers.
LO-8
8. I am familiar with the foundation of generative models.