Few-shot Learning : 基础知识
k-way n-shot Support Set :
k-way : the support set has k classes.
n-shot : every class has n samples.
Example ( six-way one-shot ) :

Another example :

随着类别(ways)数量增加 准确率会下降

随着每个类别的样本(shot)数量增加 准确率会上升

基础思想:使用简单的比较函数,对比样本


k-way n-shot Support Set :
k-way : the support set has k classes.
n-shot : every class has n samples.
Example ( six-way one-shot ) :

Another example :

随着类别(ways)数量增加 准确率会下降

随着每个类别的样本(shot)数量增加 准确率会上升

基础思想:使用简单的比较函数,对比样本

