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
0	09/10	Course Logistics + Intro to Computer Vision	PDF	​​
1	09/17	Machine Learning 101; Distinguished Talk by Prof. Rama Chellappa, University of Maryland	​PDF
2	09/24	Machine Learning 101	PDF
3	10/01	Image Representation: From Recognition to Tracking	PDF
4	10/08	Intro to Neural Networks + CNN (I)	PDF
5	10/15	Intro to Neural Networks + CNN (II); Object Detection & Segmentation (I)	PDF
6	10/22	Tutorial on Python, Git, etc
7	10/29	ICCV Week (no class)		[]
8	11/05	Object Detection & Segmentation (II) Visualization, and Adversarial Attacks of NNs	PDF
9	11/12	Generative Adversarial Networks	PDF
10	11/19	​Transfer Learning and Representation Disentanglement (I)	PDF
11	11/26	Transfer Learning and Representation Disentanglement (II)	PDF
12	12/03	Recurrent NNs and Seq-to-Seq Models (I)	PDF
13	12/10	Recurrent NNs and Seq-to-Seq Models (II)	PDF
14	12/17	Learning Beyond Images (2D/3D, depth, etc.)
15	12/24	Audio-Visual Event Localization and Synthesis
16	12/31	Few-Shot Learning for Visual Classification		[]

Contacts

Prof. Yu-Chiang Frank Wang:   ycwang@ntu.edu.tw
TA mail:                                     ntudlcvta2019@gmail.com

Teaching Assistants

Zhi-Hao Lin
BL-527
TA Hours: Mon. 11am-12pm ​

Chao-Te Chou
BL-527
TA Hours: Thur. 10am-11am ​

Ci-Siang Lin
BL-527
​TA Hours: Tue. 11am-12pm