度量学习：
度量学习作为小样本学习中主要方法之一，在解决小样本问题上应用较广，本篇博客主要介绍几篇metric learning的基础文献。
分别是：
（1）Siamese Neural Networks for One-shot Image Recognition
（2）Prototypical networks for few-shot learning
（3）Learning to Compare Relation Network for Few-Shot Learning
（4）Matching Networks for One Shot Learning
（5）Adaptive Subspaces for Few-Shot Learning