News
2022/09/08: We've taken addition ~100 students, and the registration code has been sent out to those who are admitted. If you are not added in and would like to audit the online course, please send the request to TA (with your NTU email address).
2022/09/03: For those who'd like to register the course, we will announce the registration policy at the 1st lecture on Sept. 6th.
2022/09/03: For those who'd like to register the course, we will announce the registration policy at the 1st lecture on Sept. 6th.
Introduction
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.
Goals
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.
Syllabus
Week |
Date |
Topic |
Course Materials |
Remarks |
1 |
09/06 |
Course logistics & registration; Machine Learning 101 |
||
2 |
09/13 |
Introduction to Convolutional Neural Networks (I) |
week 2 |
|
3 |
09/20 |
Introduction to Convolutional Neural Networks (II) Tutorials on Python, Github, etc. (by TAs) |
HW #1 out |
|
4 |
09/27 |
Object Detection & Segmentation; Generative Model |
||
5 |
10/04 |
Generative Adversarial Networks, and Diffusion Model |
||
6 |
10/11 |
Transfer Learning for Visual Classification & Synthesis |
HW #1 due & HW #2 out |
|
7 |
10/18 |
Guest Lecture (TBD) |
ICIP week |
|
8 |
10/25 |
Recurrent Neural Networks |
||
9 |
11/01 |
Transformer; Vision & Language (I) |
HW #2 due & HW #3 out |
|
10 |
11/08 |
Vision & Language (II); Few-Shot Learning (I) |
CVPR due |
|
11 |
11/15 |
N/A |
No class (校慶) |
|
12 |
11/22 |
3D Vision |
HW #3 due & HW #4 out |
|
13 |
11/29 |
Announcement of Final Project |
NeurIPS week & Final Projects out |
|
14 |
12/06 |
Self-Supervised Learning & Guest Lecture |
||
15 |
12/13 |
Federated Learning, Domain Generalization and More Advanced Topics |
HW #4 due |
|
17 |
12/29 Thur |
Presentation for Final Projects |
Contacts
Teaching Assistants
Zi-Ting Chou
MK-514 TA Hours: Wed. 13:20 - 14:10 |
Kai-Po Chang
MK-514 TA Hours: Thu. 14:20 - 15:10 |
I-Jieh Liu
MK-514 TA Hours: Wed. 13:20 - 14:10 |
Chi-Pin Huang
MK-514 TA Hours: Thu. 14:20 - 15:10 |
Jr-Jen Chen
MK-514 TA Hours: Tue. 12:20 - 13:10 |
Fu-Cheng Pan
MK-514 TA Hours: Fri. 12:20 - 13:10 |
Yu-Chien Liao
MK-514 TA Hours: Fri. 12:20 - 13:10 |
Yang-Che Tseng
MK-514 TA Hours: Tue. 12:20 - 13:10 |