This method transforms each $(x_i,y_i)$ into several variations as part of training data and the resulting training sample can be written as $(T(x_i), y_i)$.

Augmenting Training Data by Transforming Samples from Training Set

Instead of labeling selected data, this method augments training data by selecting data from a large set given a label, and the resulting training sample can be written as $(T(x_i), T(x_i))$. This large dataset typically has little or no label. For example, a video of a presentation contains lots of pictures of the gestures of the speaker, however, none of them are labeled. This data augmentation method uses another algorithm to learn which picture can be used for training for each label class.

Transforming Samples from a Weakly Labeled or Unlabeled Data Set

This method augments the training set by adapting training pairs $(x_i, y_i)$ from a similar dataset, and the resulting training sample can be written as $(T(x_i), T(y_i))$.

Transforming Samples from Similar Data Sets

Prior knowledge can be used to augment the training set, and below are several ways of achieving it:

1.	Transforming Samples from Training Set

2.	Transforming Samples from a Weakly Labeled or Unlabeled Data Set

3.	Transforming Samples from Similar Data Sets


University of Notre Dame

Few-Shot Learning can be divided by what part that prior knowledge has been added to:

1)	Data: The training data is augmented by prior knowledge

2)	Model: The possible model space is constrained according to prior knowledge

3)	Algorithm: The search strategy in hypothesis model space has been improved.

Another classification of Few-Shot Learning

Wang, Y., Yao, Q., Kwok, J. T., & Ni, L. M. (2020). Generalizing from a few examples: A survey on few-shot learning. ACM computing surveys (csur), 53(3), 1-34.

Generalizing from a Few Examples: A Survey on Few-Shot Learning

Ways of Augmenting Data of Few-Shot Learning

1)	Multitask Learning

2)	Embedding Learning

3)	Learning with External Memory

4)	Generative Modeling


Types of Few Shot Learning by Model

In terms of how searching strategy is affected by prior knowledge, searching algorithm motivated few-shot learning methods can be categorized as:

1)	Refining existing parameters

2)	Refining meta-learned parameters.

3)	Learning the optimizer


Learn Before

Related

Learn After