• Computer Science, Mathematics
  • Published in NIPS 2017

Prototypical Networks for Few-shot Learning

@inproceedings{Snell2017PrototypicalNF,
  title={Prototypical Networks for Few-shot Learning},
  author={Jake Snell and Kevin Swersky and Richard S. Zemel},
  booktitle={NIPS},
  year={2017}
}
A recent approach to few-shot classification called matching networks has demonstrated the benefits of coupling metric learning with a training procedure that mimics test. [...] Key Method Our method is competitive with state-of-the-art one-shot classification approaches while being much simpler and more scalable with the size of the support set. We empirically demonstrate the performance of our approach on the Omniglot and mini-ImageNet datasets. We further demonstrate that a similar idea can be used for zero…Expand Abstract

Citations

Publications citing this paper.
SHOWING 1-10 OF 778 CITATIONS

Exploiting the Matching Information in the Support Set for Few Shot Event Classification

VIEW 17 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Few-shot Learning with Multi-scale Self-supervision

VIEW 8 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Meta-Learning across Meta-Tasks for Few-Shot Learning

VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

A Closer Look at Few-shot Classification

VIEW 11 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

A New Benchmark for Evaluation of Cross-Domain Few-Shot Learning

VIEW 10 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

Associative Alignment for Few-shot Image Classification

VIEW 12 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Boosting Supervision with Self-Supervision for Few-shot Learning

VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Meta-Learning With Differentiable Convex Optimization

VIEW 12 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection

VIEW 15 EXCERPTS
CITES BACKGROUND, RESULTS & METHODS
HIGHLY INFLUENCED

Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition

VIEW 12 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2017
2020

CITATION STATISTICS

  • 226 Highly Influenced Citations

  • Averaged 240 Citations per year from 2017 through 2019

  • 158% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 32 REFERENCES

Optimization as a Model for Few-Shot Learning

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Matching Networks for One Shot Learning

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Clustering with Bregman Divergences

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Long Short-Term Memory

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Learning Deep Representations of Fine-Grained Visual Descriptions

VIEW 3 EXCERPTS

Towards a Neural Statistician

VIEW 2 EXCERPTS