Self-Training With Noisy Student Improves ImageNet Classification

Self-Training With Noisy Student Improves ImageNet Classification

Launchpad via YouTube Direct link

Introduction

1 of 10

1 of 10

Introduction

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Self-Training With Noisy Student Improves ImageNet Classification

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

  1. 1 Introduction
  2. 2 Knowledge Distillation
  3. 3 Soft and Hard labels
  4. 4 Self-training and distillation/ Noisy student
  5. 5 Algorithm: Noisy student training
  6. 6 Noise effect
  7. 7 Pseudo labels
  8. 8 Architecture
  9. 9 Experimental results
  10. 10 Robustness results

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.