DLCV - VISION & LEARNING LAB

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
3	09/29	Convolutional Neural Network (I)
4	10/06	Convolutional Neural Network (II): Visualization & Extensions of CNN
5	10/13	Tutorials on Python, Github, etc. (by TAs)
6	10/20	Object Detection & Segmentation
7	10/27	Generative Models & Generative Adversarial Network (GAN)
8	11/03	Transfer Learning for Visual Classification & Synthesis (I)		[]
9	11/10	Transfer Learning for Visual Classification & Synthesis (II); Representation Disentanglement
10	11/17	11/17 TBD (CVPR week)
11	11/24	11/24 Recurrent Neural Networks & Transformer (I)
12	12/01	11/24 Recurrent Neural Networks & Transformer (II)
13	12/08	Meta-Learning; Few-Shot and Zero-Shot Classification
14	12/15	From Domain Adaptation to Domain Generalization
15	12/22	Beyond 2D vision (3D and Depth)
16	12/29	Image Inpainting and Outpainting; Guest Lecture
17	1/05	Guest Lecture		[]