課程名稱 |
深度學習於電腦視覺 Deep Learning for Computer Vision |
開課學期 |
112-1 |
授課對象 |
學程 智慧醫療學分學程 |
授課教師 |
王鈺強 |
課號 |
CommE5052 |
課程識別碼 |
942 U0660 |
班次 |
|
學分 |
3.0 |
全/半年 |
半年 |
必/選修 |
選修 |
上課時間 |
星期二2,3,4(9:10~12:10) |
上課地點 |
博理112 |
備註 |
智慧醫療學程電資院所屬「影像」領域。 總人數上限:140人 |
|
|
課程簡介影片 |
|
核心能力關聯 |
核心能力與課程規劃關聯圖 |
課程大綱
|
為確保您我的權利,請尊重智慧財產權及不得非法影印
|
課程概述 |
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. |
課程目標 |
?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. |
課程要求 |
Engineering Mathematics (e.g., linear algebra, probability, etc.), Machine Learning (strongly suggested but optional) |
預期每週課後學習時數 |
|
Office Hours |
另約時間 |
指定閱讀 |
|
參考書目 |
|
評量方式 (僅供參考) |
|
針對學生困難提供學生調整方式 |
上課形式 |
以錄音輔助, 以錄影輔助 |
作業繳交方式 |
延長作業繳交期限 |
考試形式 |
|
其他 |
|
|
週次 |
日期 |
單元主題 |
Week 1 |
9/5 |
Course Logistics & Registration; Intro to Neural Nets |
Week 2 |
9/12 |
Convolutional Neural Networks & Training Techniques |
Week 3 |
9/19 |
Extensions of CNN & Self-Supervised Learning; Image Segmentation (HW #1 out) |
Week 4 |
9/26 |
Generative Models (I) - AE, VAE & GAN |
Week 5 |
10/3 |
ICCV week (guest lecture; Dr. Jun-Cheng Chen, Academia Sinica)
Title: An Overview of Adversarial Attack and Defense with its Application to Object Detection and Deepfake |
Week 6 |
10/10 |
No class (HW #1 due) |
Week 7 |
10/17 |
Generative Models (II) - GAN & Diffusion Model; Transfer Learning (HW #2 out) |
Week 8 |
10/24 |
Recurrent Neural Networks & Transformer |
Week 9 |
10/31 |
Vision Transformer; Vision & Language (I) - Large Language Models |
Week 10 |
11/7 |
Vision & Language (II) - Image Captioning & Visual Question Answering (HW #3 out; HW #2 due) |
Week 11 |
11/14 |
CVPR week; Guest Lecture (TBA) |
Week 12 |
11/21 |
Multimodal Learning; Parameter-Efficient Finetuning |
Week 13 |
11/28 |
3D Vision (HW #4 out; HW #3 due); Final Project Announcement |
Week 14 |
12/5 |
Federated Learning |
Week 15 |
12/12 |
NeurIPS Week; TBA (HW #4 due) |
Week 17 |
12/28 |
Final Project Presentation |
|