Timezone: »

Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks
Micah Goldblum · Steven Reich · Liam Fowl · Renkun Ni · Valeriia Cherepanova · Tom Goldstein

Thu Jul 16 06:00 AM -- 06:45 AM & Thu Jul 16 06:00 PM -- 06:45 PM (PDT) @ Virtual #None

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.

Author Information

Micah Goldblum (University of Maryland)
Steven Reich (University of Maryland)
Liam Fowl (University of Maryland)
Renkun Ni (University of Maryland)
Valeriia Cherepanova (University of Maryland)
Tom Goldstein (University of Maryland)

More from the Same Authors