Curriculum Meta-Learning for Few-shot Classification

1 code implementation • 6 Dec 2021 • Emmanouil Stergiadis, Priyanka Agrawal, Oliver Squire

As the meta-learner's goal is learning how to learn from as few samples as possible, the exact number of those samples (i. e. the size of the support set) arises as a natural proxy of a given task's difficulty.

Classification Few-Shot Image Classification +1