Introduction to Capsule Networks for Computer Vision
Offered By: University of Central Florida via YouTube
Course Description
Overview
Explore capsule networks for computer vision in this 31-minute tutorial from the CVPR 2019 conference, presented by Sara Sabour from Google. Delve into sparse pattern recognition, clutter handling, and viewpoint equivariance. Learn about coordinate frames, vector formats, and object detection through part prediction agreement. Discover capsule network concepts, including squashed capsules, dynamic routing, and EM routing for Gaussian capsules. Examine the transform, agreement, and assignment steps in routing, and observe how capsule networks generalize viewpoints and handle constellations. Gain insights into this innovative approach to computer vision that addresses limitations of traditional convolutional neural networks.
Syllabus
Intro
Exercise
Sparse Pattern Recognition
Clutter
How can we handle different viewpoints?
Viewpoint Equivariance
What stays constant?
Coordinate frame
How to work in this vector format?
How can we detect objects?
How to detect objects? • An object exists if there is agreement between multiple part predictions
Agreement and Assignment
Capsule Network
Squashed Capsules: Agreement
Squashed Capsules: Assignment Dynamic Routing
New visual symbols for clarity
EM routing for Gaussian Capsules
Transform
Agreement (M step)
Assignment (Estep)
Routing in action
Viewpoint generalization
Constellations
Taught by
UCF CRCV
Tags
Related Courses
How to Represent Part-Whole Hierarchies in a Neural Network - Geoff Hinton's Paper ExplainedYannic Kilcher via YouTube Visual Question Answering: Grounded Systems and Transformer Capsules
University of Central Florida via YouTube CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing
University of Central Florida via YouTube Subspace Capsule Network
University of Central Florida via YouTube Capsule Networks for Computer Vision – CVPR 2019 Tutorial
University of Central Florida via YouTube