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 $$(T(x_i), T(y_i))$$.

University of Notre Dame

Google

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


Ways of Augmenting Data 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

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

Augmenting Training Data by Transforming Samples from Similar Data Sets

In few-shot learning, instead of manually labeling selected data, this method augments training data by selecting samples from a large weakly labeled or unlabeled dataset given a label. The resulting training sample can be written as $$(T(x_i), T(x_i))$$. For example, a presentation video contains many unlabeled pictures of the speaker's gestures. This data augmentation method uses another algorithm to learn which picture can be used for training for each label class.

Learn Before

Related