Unsupervised Meta-Learning for Few-Shot Image Classification

Unsupervised Meta-Learning for Few-Shot Image Classification

UCF CRCV via YouTube Direct link

Outline

2 of 18

2 of 18

Outline

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Unsupervised Meta-Learning for Few-Shot Image Classification

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Outline
  3. 3 Problem definition
  4. 4 What is a task?
  5. 5 What we learn during meta-learning?
  6. 6 Model-agnostic meta-learning
  7. 7 Action recognition
  8. 8 Unsupervised Meta-learning with Tasks constructe by Random sampling and Augmentation UMTRA
  9. 9 Omniglot augmentation
  10. 10 Auto augmentation
  11. 11 ImageNet augmentation
  12. 12 Few-shot learning benchmarks
  13. 13 Ablation studies Omniglot
  14. 14 Ablation studies Mini-Imagenet
  15. 15 CelebA task generation
  16. 16 Video augmentation (self supervision)
  17. 17 Features visualization by t-SNE
  18. 18 t-SNE visualization of the last hidden layer

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.