BriefGPT.xyz
Mar, 2017
少样本学习的原型网络
Prototypical Networks for Few-shot Learning
HTML
PDF
Jake Snell, Kevin Swersky, Richard S. Zemel
TL;DR
本文提出一种少样本学习方法，即使用原型网络从小样本中抽象出原型，将其映射到一个度量空间中，比较测试样本和原型之间的距离来进行分类，同时还将其拓展到零样本学习，取得了最先进的结果。
Abstract
We propose
prototypical networks
for the problem of
few-shot classification
, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class
→