Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks

ICML 2020

Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks

Jul 12, 2020
|
26 views
|
Details
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 develop several hypotheses for why meta-learned models perform better. In addition to visualizations, we design several regularizers inspired by our hypotheses which improve performance on few-shot classification. Speakers: Micah Goldblum, Liam Fowl, Renkun Ni, Steven Reich, Valeriia Cherepanova, Tom Goldstein

Comments
loading...