Computer Vision

A Computer Vision Sampler

Announcements:

Lectures on Zoom

Following Duke guidelines, the course resumes as a recurring virtual Zoom meeting after Spring break. Join the course on Sakai.

Homework

Homework 6 is available on the class homework page.

Exams

There is a midterm exam on Tuesday, March 3rd, from 10:05am to 11:20am and a final exam on Wednesday, April 29th, from 2:00pm to 4:00pm (two hours). Both exams are in the regular lecture classroom. The schedule for the final is set by Duke's Registrar.

Piazza

We will use Piazza to communicate with each other outside of class. Sign up for Piazza here the first time if you haven't already.

Error rates (green bars) on a standard image classification benchmark have decreased rapidly in the last few years. AlexNet (2012) was the first deep network used on this task. While not the first deep network in computer vision, AlexNet improved image recognition performance overnight, and attracted many computer vision researchers to deep learning. Networks have become by-and-large deeper and deeper since then (red plot). This figure is from a 2018 survey on deep learning by Samira Pouyanfar et al.

This course explores concepts in visual recognition, visual motion analysis, and visual reconstruction through a sample of techniques. There will be lectures, class discussion, and homework.

The class meets in room 2231 of the French Science Center Building.

COMPSCI 527, Duke University, Site based on the fluid 960 grid system