In this course, our goal is to learn the fundamental elements of image processing. Among the various subfields of image processing and computer vision, this class will focus on the basics of Autoencoder structures and image generation. Rather than delving deeply into complex mathematical equations, we will introduce key ideas, architectural concepts, and workflows. In the early semester, our course will initially concentrate on explaining Convolutional modules to help students understand the underlying structures. In the mid to later semester, the focus will shift towards deep learning architectures, covering essential concepts and structures in the context of image processing and generation.
Class time and location: Tuesday 13:30~14:45 / Thursday 13:30~14:45 - 209관 101호 <창의융합프로젝트 세미나실>
Textbook (Reference): Deep Learning: GoodFellow
Repository: https://github.com/PiLab-CAU/ImageProcessing-2402
Tuesday: 16:00~17:00, 305관 712호
Attendance: 10%
Midterm Exam: 35%
Final Exam: 45%
(Additional) Participation score: 10%
Opening an Issue: 3%
Add discussion comments: 1%
Attendance policy: Accept <=1/4 absent overall class. Offline Attendance check.