DLCV - VISION & LEARNING LAB

News

2023/09/08: We have email the permission code (>60) to those who are additionally selected to be registered. If you change your mind and do not need to register the course anymore, please notify the TA by the end of this week. If you are not able to register but would like to audit the course via NTU COOL, please send your request to the TA directly.

2023/08/01: For those who'd like to register the course but are not in, we will announce the registration policy at the 1st lecture on Sept. 5th.

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 deep learning models, with particular focuses on understanding and designing such models for solving various computer vision tasks.

Goals

This course will expose students to cutting-edge research — starting from fundamentals of deep learning to its recent advances such as generative AI models. 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	09/05	Course Logistics & Registration; Intro to Neural Nets	W1-1 W1-2
2	09/12	Convolutional Neural Networks & Training Techniques	W2
3	09/19	Extensions of CNN & Self-Supervised Learning; Image Segmentation	W3	HW #1 out
4	09/26	Generative Models (I) - AE, VAE & GAN
5	10/03	Guest Lecture (Dr. Jun-Cheng Chen, Academia Sinica)		ICCV week
6	10/10	No Class		Double Tenth Day;
7	10/17	Generative Models (II) - GAN & Diffusion Model; Transfer Learning		HW #1 due & HW #2 out
8	10/24	Recurrent Neural Networks & Transformer
9	10/31	Vision Transformer; Vision & Language (I) - Large Language Models
10	11/07	Vision & Language (II) - Image Captioning & Visual Question Answering		HW #2 due & HW #3 out
11	11/14	Guest Lecture (TBA)		CVPR week
12	11/21	Multimodal Learning; Parameter-Efficient Finetuning
13	11/28	3D Vision		HW #3 due & HW #4 out Final Projects out
14	12/05	Federated Learning & Advanced Topics
15	12/12	TBA		NeurIPS week HW #4 due
17	12/28 Thur	Final Project Presentation