Proto

Prototypical Networks for Few-shot Learning

Introduction

Name:	Prototypical Networks
Embed.:	Conv64F
Type:	Metric
Venue:	NeurIPS'17
Codes:	Prototypical-Networks-for-Few-shot-Learning-PyTorch

Cite this work with:

@inproceedings{DBLP:conf/nips/SnellSZ17,
  author    = {Jake Snell and
               Kevin Swersky and
               Richard S. Zemel},
  title     = {Prototypical Networks for Few-shot Learning},
  booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference
               on Neural Information Processing Systems 2017, December 4-9, 2017,
               Long Beach, CA, {USA}},
  pages     = {4077--4087},
  year      = {2017},
  url       = {https://proceedings.neurips.cc/paper/2017/hash/cb8da6767461f2812ae4290eac7cbc42-Abstract.html}
}

---

Results and Models

Classification

	Embedding	📖 miniImageNet (5,1)	💻 miniImageNet (5,1)	📖miniImageNet (5,5)	💻 miniImageNet (5,5)	📝 Comments
1	Conv64F	-	47.05 ± 0.35 ⬇️ 📋	-	68.56 ± 0.16 ⬇️ 📋	Table.2
2	ResNet12	-	54.25 ± 0.37 ⬇️ 📋	-	74.65 ± 0.29 ⬇️ 📋	Table.2

	Embedding	📖 tieredImageNet (5,1)	💻 tieredImageNet (5,1)	📖tieredImageNet (5,5)	💻 tieredImageNet (5,5)	📝 Comments
1	Conv64F	-	46.11 ± 0.39 ⬇️ 📋	-	70.07 ± 0.34 ⬇️ 📋	Table.2