Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning. (arXiv:2201.05151v1 [cs.CV])

Modern deep learning requires large-scale extensively labelled datasets for
training. Few-shot learning aims to alleviate this issue by learning
effectively from few labelled examples. In previously proposed few-shot visual
classifiers, it is assumed that the feature manifold, where classifier
decisions are made, has uncorrelated feature dimensions and uniform feature
variance. In this work, we focus on addressing the limitations arising from
this assumption by proposing a variance-sensitive class of models that operates
in a low-label regime. The first method, Simple …

arxiv cv few-shot learning learning meta meta-learning