Timezone: »

 
Poster
Prototypical Networks for Few-shot Learning
Jake Snell · Kevin Swersky · Richard Zemel

Mon Dec 04 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #118
in Posters Mon »

We propose Prototypical Networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class. Prototypical Networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve excellent results. We provide an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning. We further extend Prototypical Networks to zero-shot learning and achieve state-of-the-art results on the CU-Birds dataset.

Keywords: One-Shot/Low-Shot Learning Approaches · Embedding Approaches · Metric Learning
[ Code]  [ Paper] 

Author Information

Jake Snell (University of Toronto, Vector Institute)
Kevin Swersky (Google)
Richard Zemel (Vector Institute/University of Toronto)

More from the Same Authors