NTU 课程笔记:self-supervised learning

1 为什么需要 self-supervision?

  • 为每个新的任务都创建一个新的数据集,开销是很大的
  • 有些领域标注是很稀缺的(比如医疗领域)
  • 有些领域 数据集太大,来不及标注
  • self-supervision 很像婴儿学习的方式

2 什么是self-supervison

  • A form of unsupervised learning where the data provides the supervision(用数据本身创造label)
  • In general, withhold some part of the data, and task the network with predicting it
  • The task defines a proxy loss, and the network is forced to learn what we really
    care about, e.g. a semantic representation, in order to solve it(proxy loss~~text loss)

Guess you like

Origin blog.csdn.net/qq_40206371/article/details/121285762