Meta-learning algorithms produce feature extractors which achieve state-of-the-art performance on few-shot classification. While the literature is rich with meta-learning methods, little is known about why the resulting feature extractors perform so well. We develop a better understanding of the underlying mechanics of meta-learning and the difference between models trained using meta-learning and models which are trained classically. In doing so, we introduce and verify several hypotheses for why meta-learned models perform better. Furthermore, we develop a regularizer which boosts the performance of standard training routines for few-shot classification. In many cases, our routine outperforms meta-learning while simultaneously running an order of magnitude faster.
@article{arxiv.2002.06753,
title = {Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks},
author = {Micah Goldblum and Steven Reich and Liam Fowl and Renkun Ni and Valeriia Cherepanova and Tom Goldstein},
journal= {arXiv preprint arXiv:2002.06753},
year = {2020}
}