Prototypical Networks for Few-shot Learning

Jake Snell, Kevin Swersky, Richard S. Zemel
3/15/2017
cs.LGstat.ML

Official code: jakesnell/prototypical-networks (1,234 stars, MIT, PyTorch, last commit 2021-01-28).

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.

View on arXivView PDF

Code Implementations(1)

jakesnell/prototypical-networksOfficial100%
PyTorchMIT

Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"

1,234270Shell, PythonNov 5, 20175 years agoMIT
deep-learningfew-shotmetric-learningnips-2017omniglot+1 more

Similar Papers

A Closer Look at Few-shot Classification

89% match1 repo1.2k2019

SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning

88% match1 repo1342019

What Makes for Effective Few-shot Point Cloud Classification?

87% match1 repo172023

Universal Representation Learning from Multiple Domains for Few-shot Classification

87% match2 repos8032021

Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph

86% match1 repo562019

Few-shot Classification via Ensemble Learning with Multi-Order Statistics

86% match2023

Cite this paper

@article{snell2017prototypical,
  title  = {Prototypical Networks for Few-shot Learning},
  author = {Jake Snell and Kevin Swersky and Richard S. Zemel},
  year   = {2017},
  eprint = {1703.05175},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1703.05175}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1703.05175.svg)](https://codeofpaper.com/paper/1703.05175)

Discussion