VISION & LEARNING LAB
  • Home
  • About
  • Members
    • ​Laboratory Director
    • Assistants
    • Students
  • Publications
  • Courses
    • DLCV
  • Maintenance
  • Others

Deep Learning for Computer Vision 
Fall  2020

9/18 update: We have already notified all the students who have been selected and are eligible for enrollment. Please check the email you filled in the registration form.

For NTU students who would like to take this course but are not registered yet, please complete and submit the registration form https://forms.gle/EaDTf4oG8aNZGZDX7 between 9/14 Mon 9 a.m. and 9/15 Tue 23:59 Taiwan time. We will notify the registration results by email no later than 9/18 5 p.m.

Due to space limit, NO sit-in is allowed.

Introduction

Computer Vision has become ubiquitous in our society, with applications in image/video search and understanding, apps, mapping, medicine, drones, and self-driving cars. Core to many of these applications are visual recognition tasks such as image classification, segmentation, localization and detection. Recent developments in neural network (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 details of the deep learning architectures with a focus on learning end-to-end models for solving these 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. The emphasis will be on student-led paper presentations and discussions. Each topic will begin with instructor lectures to present context and background material. 

Syllabus 

Week
Date
Topic
Course Materials
Remarks
1
09/15
Course Logistics
DLCV_W0​
​​
2
09/22
Machine Learning 101
DLCV_W1​ 
 
3
09/29
Intro to Neural Networks; Convolutional Neural Network (I)
DLCV_W2
HW #1 out
4
10/06
Convolutional Neural Network (II): Visualization & Extensions of CNN
DLCV_W3
 
5
10/13
Tutorials on Python, Github, etc. (by TAs)
DLCV_W4
HW #1 due 
6
10/20
 Visualization of CNN (II); Object Detection & Segmentation
DLCV_W5
HW #2 out
7
10/27
Image Segmentation; Generative Models
DLCV_W6
 
8
11/03
Generative Adversarial Network (GAN)
DLCV_W7
[] 
9
11/10
Transfer Learning for Visual Classification & Synthesis; Representation Disentanglement
DLCV_W8
HW #2 due;
​HW #3 out
10
11/17
Guest Lectures (Dr. Trista Chen & David Chou) 
 
 
11
11/24
Representation Disentanglement; Recurrent Neural Networks & Transformer (I)
DLCV_W10
 
12
12/01
Recurrent Neural Networks & Transformer (I) Meta-Learning; Few-Shot and Zero-Shot Classification (I)
DLCV_W11
HW #3 due
13
12/08
Meta-Learning; Few-Shot and Zero-Shot Classification (II)
DLCV_W12
HW #4 out
14
12/15
From Domain Adaptation to Domain Generalization
DLCV_W13
Team-up for Final Projects
15
12/22
Beyond 2D vision (3D and Depth)
 
 
16
12/29
Image Inpainting and Outpainting; Guest Lecture
 
HW #4 due​ 
17
1/05
Guest Lectures
 
[]
 
1/18-22
Presentation for Final Projects
 
TBD

Contacts

Prof. Yu-Chiang Frank Wang:   ycwang@ntu.edu.tw
TA mail:                                     ntudlcv@gmail.com

Teaching Assistants

Picture
Sheng-Yu Huang
BL-527
TA Hours: ​Thu. 15:00~16:00
圖片
Yu-Shan Huang
BL-527
TA Hours:​ Tue. 13:00~14:00
Picture
Wan-Cyuan Fan
BL-527
​TA Hours: Wed. 13:00~14:00
圖片
Zu-Yun Shiau
BL-527
​TA Hours: 
​Mon. 15:00~16:00
圖片
圖片
圖片
Cheng-Fu Yang
BL-527
TA Hours: ​Fri. 11:00~12:00
Cheng-Yo (Ugo) Tan 
BL-527
TA Hours: ​Wed. 16:00~17:00
Chiao-An Yang
BL-527
TA Hours: ​Wed. 14:00~15:00


​博理館 527 室 (BL 527) @ NTU

Contact Us
Tel: 02-3366-3700 #6527
​Admin. Assistant: Fang-Ru Shih (frs106 AT ntu.edu.tw)
Web Admin. : Yen-Cheng Liu (ycliu93 AT ntu.edu.tw)
Web Photo Credit: Yuan-Fang Lin (b02901003 AT ntu.edu.tw)


​

  • Home
  • About
  • Members
    • ​Laboratory Director
    • Assistants
    • Students
  • Publications
  • Courses
    • DLCV
  • Maintenance
  • Others