Prototypical Networks for Few-shot Learning

TL;DR

Prototypical networks introduce a simple metric-based approach for few-shot and zero-shot learning, achieving state-of-the-art results by learning class prototypes in a learned metric space.

Contribution

The paper presents a novel, simple method for few-shot and zero-shot classification using prototype representations, outperforming more complex approaches.

Findings

Achieved state-of-the-art results on CU-Birds dataset.

Simple design decisions significantly improve performance.

Effective for both few-shot and zero-shot 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.