07 自己教師あり学習の画像セグメンテーションへの適用


本資料は2020年7月2日に社内共有資料として展開していたものを WEBページ向けにリニューアルした内容になります。



■Agenda

 

Introduction

  • Image Segmentation

  • Problems

  • Self-supervised learning

  • Content of this presentation

Survey

  • Pseudo Labeling

  • Class Activation Map

  • Image Depth Information

  • How about using videos

Some comments



■Image Segmentation

 


■Problems

 

●very hard to annotate (=expensive)

  • pixel-wise annotation

  • different types of objects

  • boundaries are often blurry

●easy to make mistake

  • lots of unclear cases

  • Need to keep focus for long time


How can we change this situation?



■Self-supervised learning

 
  • Research topic pushed by “godfathers of AI” and specially by Yann Le Cun

  • Pre-train a feature extractor in an unsupervised way then train the classifier with annotated data

  • Reach SOTA with only 10% of labels in the last papers (starting to go beyond)

  • Methods coming from NLP