Corpus ID: 19524161

Gaussian Prototypical Networks for Few-Shot Learning on Omniglot

@article{Fort2017GaussianPN,
  title={Gaussian Prototypical Networks for Few-Shot Learning on Omniglot},
  author={Stanislav Fort},
  journal={ArXiv},
  year={2017},
  volume={abs/1708.02735}
}
  • Stanislav Fort
  • Published 2017
  • Computer Science, Mathematics
  • ArXiv
  • We propose a novel architecture for k-shot classification on the Omniglot dataset. Building on prototypical networks, we extend their architecture to what we call Gaussian prototypical networks. Prototypical networks learn a map between images and embedding vectors, and use their clustering for classification. In our model, a part of the encoder output is interpreted as a confidence region estimate about the embedding point, and expressed as a Gaussian covariance matrix. Our network then… CONTINUE READING
    One-Way Prototypical Networks
    • 4
    • PDF
    Improved Few-Shot Visual Classification
    • 3
    • PDF
    Looking back to lower-level information in few-shot learning
    Comparative Analysis on Classical Meta-Metric Models for Few-Shot Learning
    Stochastic Prototype Embeddings
    • 1
    • PDF
    MxML: Mixture of Meta-Learners for Few-Shot Classification
    • 4
    • PDF
    Large Margin Few-Shot Learning
    • 10
    • PDF
    Few-Shot Learning for Dermatological Disease Diagnosis
    • 7
    • Highly Influenced
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 24 REFERENCES
    Prototypical Networks for Few-shot Learning
    • 1,497
    • Highly Influential
    • PDF
    Siamese Neural Networks for One-Shot Image Recognition
    • Gregory R. Koch
    • Computer Science
    • 2015
    • 1,270
    • PDF
    Matching Networks for One Shot Learning
    • 1,858
    • PDF
    Optimization as a Model for Few-Shot Learning
    • 1,184
    Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
    • 2,269
    • PDF
    Towards a Neural Statistician
    • 203
    • PDF
    One shot learning of simple visual concepts
    • 384
    • PDF
    Meta-Learning with Temporal Convolutions
    • 131
    • PDF
    Meta Networks
    • 289
    • PDF