DLCV - VISION & LEARNING LAB

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
000000	03/07	Course Logistics + Intro to Computer Vision	[Slides]	[]
1	03/14	Machine Learning 101	[Slides]	HW #1 out
2	03/21	Image Representation	[Slides]	HW #1 due
3	03/28	Interest Point: From Recognition to Tracking	[Slides]	HW #2 out
4	04/04	N/A	[]	Spring Break
5	04/11	Intro to Neural Networks + CNN	[Slides]	HW #2 due
6	04/18	Detection & Segmentation	[Slides]	HW #3 out
7	04/25	Generative Models	[Slides]	[]
8	05/02	Visualization and Understanding NNs	[Slides]	HW #3 due / HW #4 out
9	05/09	Recurrent NNs and Seq-to-Seq Models (I)	[Slides]	Project team
10	05/16	Recurrent NNs and Seq-to-Seq Models (II)	[Slides]	HW #4 due / HW #5 out
11	05/23	Deep Reinforcement Learning for Visual Applications	[Slides]	Project proposal
12	05/30	Learning Beyond Images (2D/3D, depth, etc.)	[]	[]
13	06/06	Transfer Learning for Visual Analysis	[]	HW #5 due
14	06/13	Vision & Language / Guest Lectures	[]	Project midterm progress
15	06/20	Industrial Visit (e.g., Microsoft @ TPE)	[]	CVPR week
16	06/27	Final Project Presentation	[]	[]