Skip to yearly menu bar Skip to main content


Poster

Prototypical Networks for Few-shot Learning

Jake Snell · Kevin Swersky · Richard Zemel

Pacific Ballroom #118

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


Abstract:

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.

Live content is unavailable. Log in and register to view live content