|
課程名稱 |
電腦視覺實務與深度學習
Computer Vision Practice with Deep Learning |
|
開課學期 |
111-2 |
|
授課對象 |
電機資訊學院 資訊網路與多媒體研究所 |
|
授課教師 |
鄭文皇 |
|
課號 |
CSIE5428 |
|
課程識別碼 |
922 U4850 |
|
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 |
資103 |
|
備註 |
建議修過深度學習。
限學士班三年級以上
總人數上限：120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 |
電腦視覺已經深入生活當中，然而在不同應用情境下存在不同的實務挑戰，本課程講授學術文獻上以深度學習為主流之最新電腦視覺技術解決方案，以期建立修課學生之電腦視覺學理基礎與實務應用能力。 |
|
課程目標 |
．︁This course will provide a pragmatic introduction to computer vision, with an aim to walk through milestone models and research papers in the literature.
．︁This course will explore practical solutions from the latest literature for solving computer vision tasks with various data, label, and deployment constrains. |
|
課程要求 |
|
|
預期每週課後學習時數 |
|
|
Office Hours |
另約時間 備註： Please contact the teacher or TAs for making an appointment |
|
指定閱讀 |
|
|
參考書目 |
Richard Szeliski, “Computer Vision: Algorithms and Applications, 2nd ed.,” Springer, 2022. |
|
評量方式
(僅供參考) |
|
No. |
項目 |
百分比 |
說明 |
|
1. |
Assignments |
50% |
6 times, announced in class or from the course website
|
2. |
Class Participation |
10% |
Only applicable for “Invited Talks” |
3. |
Final Projects |
40% |
Team-based presentation with a proof-of-concept implementation of a selected ‘top-level’ and ‘new’ (published from 2022 or after) paper, which must be enhanced by the team’s own innovations |
|
|
週次 |
日期 |
單元主題 |
|
第01週 |
02/21 |
Course Overview |
|
第02週 |
02/28 |
和平紀念日(放假日) |
|
第03週 |
03/07 |
Generic Object Detection:
Convolutional Neural Networks (CNN) & Transformer Networks |
|
第04週 |
03/14 |
Generic Object Detection:
CNN-Transformer Hybrid Models |
|
第05週 |
03/21 |
Generic Object Detection:
Diffusion Models & Foundation Models |
|
第06週 |
03/28 |
Practical Issues:
Lightweight Computer Vision |
|
第07週 |
04/04 |
兒童節(放假日) |
|
第08週 |
04/11 |
Practical Issues:
Data Imbalance and Domain Adaptation |
|
第09週 |
04/18 |
Practical Issues:
Weakly-/ Semi-supervised Learning in Computer Vision |
|
第10週 |
04/25 |
Practical Issues:
Self-supervised Learning in Computer Vision |
|
第11週 |
05/02 |
Generative Computer Vision:
Unconditional Generative Models |
|
第12週 |
05/09 |
Generative Computer Vision:
Multimodal Learning for Generation |
|
第13週 |
05/16 |
Generative Computer Vision:
Conditional Generative Models |
|
第14週 |
05/23 |
Invited Talks |
|
第15週 |
05/30 |
Final Projects (I) |
|
第16週 |
06/06 |
Final Projects (II) |
|