Completed
Intro
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Introduction to Capsule Networks for Computer Vision
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Exercise
- 3 Sparse Pattern Recognition
- 4 Clutter
- 5 How can we handle different viewpoints?
- 6 Viewpoint Equivariance
- 7 What stays constant?
- 8 Coordinate frame
- 9 How to work in this vector format?
- 10 How can we detect objects?
- 11 How to detect objects? • An object exists if there is agreement between multiple part predictions
- 12 Agreement and Assignment
- 13 Capsule Network
- 14 Squashed Capsules: Agreement
- 15 Squashed Capsules: Assignment Dynamic Routing
- 16 New visual symbols for clarity
- 17 EM routing for Gaussian Capsules
- 18 Transform
- 19 Agreement (M step)
- 20 Assignment (Estep)
- 21 Routing in action
- 22 Viewpoint generalization
- 23 Constellations