Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation

Posted 爆米花好美啊

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation相关的知识,希望对你有一定的参考价值。

  • Loss Source 1: Cross entropy loss,各个阶段的分类器都有
  • Loss Source 2: KL loss,深层的分类器作为浅层分类器的teacher
  • Loss Source 3: L2 loss from hints,深层分类器的特征和浅层分类器的特征做L2 loss,bottleneck即feature adaptation,为了使student和teacher一样大



以上是关于Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation的主要内容,如果未能解决你的问题,请参考以下文章

Paddle your own canoe.

Design Your Own Protocol In Five Minutes

Build your own distribution based on Fedora CoreOS

Build your own distribution based on Fedora CoreOS

Perl 5 的 pick-your-own-quotes 运算符的合法分隔符是啥?

Creating your own header file in C