Course Syllabus
The syllabuses on both this page and the NTU online course information are synchronized.
Course Information
| Item | Content |
| Course title | Deep Learning for Computer Vision |
| Semester | 110-1 |
| Designated for |
Intelligent Medicine Program GRADUATE INSTITUTE OF COMMUNICATION ENGINEERING GRADUATE INSTITUTE OF ELECTRICAL ENGINEERING |
| Instructor | YU-CHIANG WANG |
| Curriculum No. | CommE 5052 |
| Curriculum Id No. | 942 U0660 |
| Class | |
| Credit | 3 |
| Full/Half Yr. | Half |
| Required/Elective | Elective |
| Time | Tuesday 7,8,9(14:20~17:20) |
| Place | 博理113 |
| Remarks | The course is conducted in English。 |
Course Syllabus
| Item | Content |
| Course Description | Computer vision has become ubiquitous in our society, with a variety of applications in image/video search and understanding, medicine, drones, and self-driving cars. As the core to many of the above applications, visual analysis such as image classification, segmentation, localization and detection would be among the well-known problems in computer vision. Recent developments in neural networks (a.k.a. deep learning) approaches have greatly advanced the performance of these state-of-the-art visual recognition systems. This course is a deep dive into the details of deep learning architectures, with a particular focus on understanding and designing learnable models for solving various vision tasks. |
| Course Objective | This course will expose students to cutting-edge research — starting from a refresher in basics of machine learning, computer vision, neural networks, to recent developments. Each topic will begin with instructor lectures to present context and background material, followed by discussions and homework assignments, allowing the students to develop hand-on experiences on deep learning techniques for solving practical computer vision problems. |
| Course Requirement | Engineering Mathematics (e.g., linear algebra, probability, etc.), Machine Learning (strongly suggested but optional) |
| References | |
| Designated Reading |
Progress
| Week | Date | Topic |
| Week 1 | 9/28 | Course logistics & registration; Machine Learning 101 (HW #0 out) |
| Week 2 | 10/5 | Introduction to Convolutional Neural Networks (I) (HW #0 due on 10/8 Fri 23:59) |
| Week 3 | 10/12 | Introduction to Convolutional Neural Networks (II) |
| Week 4 | 10/19 | Object Detection & Segmentation |
| Week 5 | 10/26 | Generative Models & Generative Adversarial Networks |
| Week 6 | 11/2 | Transfer Learning for Visual Classification & Synthesis (I) |
| Week 7 | 11/9 | Transfer Learning for Visual Classification & Synthesis (II) |
| Week 8 | 11/16 | TBD (CVPR week) |
| Week 9 | 11/23 | Recurrent Neural Networks & Transformer (I) |
| Week 10 | 11/30 | Recurrent Neural Networks & Transformer (II) |
| Week 11 | 12/7 | Meta-Learning for Visual Analysis (I) |
| Week 12 | 12/14 | Meta-Learning for Visual Analysis (II) |
| Week 13 | 12/21 | From Zero-Shot Learning to Explainable AI |
| Week 14 | 12/28 | Beyond 2D Vision (3D and Depth) |
| Week 15 | 1/4 | Vision and Language |
| Week 16 | 1/11 | Guest Lecture (TBD) |
Grading
| NO | Item | Pc | Explanations for the conditions |
| 1 | HWs | 67% | HW #0 (required but 0%), HW #1 (15%), HW #2 (16%), HW #3 (18%), HW #4 (18%), and HW #5 (bonus & optional, up to 5%) |
| 2 | Final Projects | 33% | Lecturer and TAs ratings + inter & intra-group evaluation |
Office Hour
| NO | Day | Start time | End time |
| Remarks | Our first class starts on 9/28 Tue. For those who are not registered and would like to sign up, please fill in the online registration form at https://forms.gle/quFfkKvX7HESAaWH7 from 9/28 Tue 2:20pm to 11:59pm Taiwan time (GMT+8). No late request would be accepted. |