Course: Selected Topics in Visual Recognition using Deep Learning

Instructor: Prof. Yen-Yu Lin

Introduction

Visual recognition aims to enable computers to see, understand, and interpret the world like human visual systems. Deep learning technologies are at the core of the current machine vision revolution. Large-scale annotated data and affordable GPU hardware jointly allow the training of deep learning models with hundreds of layers and millions of parameters, which greatly improve the performance of various machine vision applications and even initiate new vision applications.

Office Hours

Thursday 3:00 pm ~ 4:00 pm at EC118

Please contact instructor Yen-Yu Lin at [email protected] or TA Jimmy Yang at [email protected]

Grading Policy

• 4 homework assignments: 72%, see HW READEME
• Final project: 28%

Syllabus

Week	Date	Topic	Remarks
1	09/12	Introduction to Visual Recognition
2	09/19	Conventional Machine Learning vs. Deep Learning
3	09/26	Convolutional Neural Networks (CNN)	HW1 anoounce
4	10/03	Representative CNN Architectures
5	10/10	National Holiday (Double tenth)
6	10/17	Generative Adversarial Learning and Recurrent Neural Networks	HW1 due, HW2 announce
7	10/24	Object Detection / Semantic Segmentation
8	10/31	Guest Lectures
9	11/07	Semantic Segmentation	HW2 due, HW3 announce
10	11/14	Image Super-resolution
11	11/21	Image Matching and Alignment
12	11/28	Action and Gesture Recognition	HW3 due, Final project announce, HW4 announce
13	12/05	3D Point Classification and Segmentation
14	12/12	Guest Lectures II
15	12/19	Image Style Transfer, Video Frame Interpolation and Video Synthesis	HW4 due
16	12/26	Final project presentation I
17	01/02	Final project presentation II