一、一些方法

三元组网络？

1. 孪生网络 siameseNN-fewshot

代码：https://github.com/JustinYuu/siameseNN-fewshot
论文：https://www.cs.cmu.edu/~rsalakhu/papers/oneshot1.pdf

2. MAML 模型无关元学习 2017

论文及代码讲解：https://zhuanlan.zhihu.com/p/66926599
代码：https://github.com/dragen1860/MAML-Pytorch
某大佬实现：https://github.com/Miaotxy/my_pytorch_maml

3. Prototypical-Networks 原型网络 2017

https://paperswithcode.com/paper/prototypical-networks-for-few-shot-learning#code
https://github.com/orobix/Prototypical-Networks-for-Few-shot-Learning-PyTorch

4. A New Meta-Baseline for Few-Shot Learning

https://github.com/yinboc/few-shot-meta-baseline

5. learn2learn 软件库

https://github.com/learnables/learn2learn

6. 少样本目标检测

https://github.com/ucbdrive/few-shot-object-detection

元学习pytorch有关的git网址 Torchmeta: A Meta-Learning library for PyTorch
https://github.com/tristandeleu/pytorch-meta

https://github.com/cnguyen10/few_shot_meta_learning

https://github.com/jiangxinyang227/few_shot_learning

知乎少样本学习方法整理（比较好）

https://zhuanlan.zhihu.com/p/129261297?utm_source=com.alibaba.android.rimet

数据集

Omniglot
MiniImagenet