DLCV - VISION & LEARNING LAB

News

2021/10/1: We have just sent out the notification emails to those who signed up the registration form and got accepted. If you did not receive the notification email and would like to audit the online course, please email the TA (NTU email account required).

2021/9/27: The link to the online course for the first three weeks is here. The slides and materials for the first lecture and HW #0 are now available.

2021/9/21: 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.

2021/9/13: The syllabus is updated. Following NTU's COVID policy, we will only offer online lectures for the first three weeks of the class (i.e., 9/28, 10/5, and 10/12). More information about the policy for students attending physical lectures will be released once available (but NO sit-in will be allowed).

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	9/28	Course logistics & registration & Machine Learning 101	week 1-1 week 1-2	HW #0 out
2	10/05	Introduction to Convolutional Neural Networks (I)	week 2	HW #0 due (10/8 Fri 23:59)
3	10/12	Introduction to Convolutional Neural Networks (II) Tutorials on Python, Github, etc. (by TAs)	week 3	HW #1 out
4	10/19	Visualization of CNN; Object Detection & Segmentation (I)	week 4
5	10/26	Object Detection & Segmentation (II); Generative Models & Generative Adversarial Networks (I)	week 5
6	11/02	Generative Models & Generative Adversarial Networks (II) Transfer Learning for Visual Classification & Synthesis (I)		HW #1 due; HW #2 out
7	11/09	Transfer Learning for Visual Classification & Synthesis (II)
8	11/16	TBD (CVPR week)
9	11/23	Recurrent Neural Networks & Transformer (I)		HW #2 due; HW #3 out
10	11/30	Recurrent Neural Networks & Transformer (II)
11	12/07	Meta-Learning for Visual Analysis (I)		Final Project Announcement
12	12/14	Meta-Learning for Visual Analysis (II)		HW #3 due; HW #4 out
13	12/21	Self-Supervised Learning for Visual Analysis
14	12/28	Beyond 2D Vision (3D and Depth)		HW #5-1 out (bonus)
15	01/04	Vision and Language		HW #4 due; HW #5-2 out (bonus)
16	01/11	Guest Lecture (TBD)		HW #5 due
17	01/18	Presentation for Final Projects