Corpus ID: 309759

Prototypical Networks for Few-shot Learning

@inproceedings{Snell2017PrototypicalNF,
  title={Prototypical Networks for Few-shot Learning},
  author={J. Snell and Kevin Swersky and R. 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
2,085 Citations
Prototypical Siamese Networks for Few-shot Learning
  • Jun-hua Wang, Yongping Zhai
  • Computer Science
  • 2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)
  • 2020
  • 8
Regression Networks for Meta-Learning Few-Shot Classification
  • 4
  • Highly Influenced
  • PDF
Transductive Prototypical Network For Few-Shot Classification
  • Highly Influenced
Learning to Compare: Relation Network for Few-Shot Learning
  • 1,131
  • Highly Influenced
  • PDF
Meta-Relation Networks for Few Shot Learning
Subspace Networks for Few-shot Classification
  • 8
One-Way Prototypical Networks
  • 6
  • PDF
Prototypical Bregman Networks
  • Highly Influenced
Meta-Learning for Semi-Supervised Few-Shot Classification
  • 388
  • PDF
Simultaneous Perturbation Stochastic Approximation for Few-Shot Learning
  • 1
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 43 REFERENCES
Siamese Neural Networks for One-Shot Image Recognition
  • 1,729
  • PDF
Optimization as a Model for Few-Shot Learning
  • 1,495
  • Highly Influential
Matching Networks for One Shot Learning
  • 2,415
  • Highly Influential
  • PDF
Write a Classifier: Zero-Shot Learning Using Purely Textual Descriptions
  • 232
  • PDF
Synthesized Classifiers for Zero-Shot Learning
  • 482
  • PDF
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
  • 3,113
  • PDF
Evaluation of output embeddings for fine-grained image classification
  • 631
  • PDF
Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions
  • 292
  • PDF
Towards a Neural Statistician
  • 250
  • Highly Influential
  • PDF
One shot learning of simple visual concepts
  • 468
  • PDF
...
1
2
3
4
5
...