• Corpus ID: 19524161

Gaussian Prototypical Networks for Few-Shot Learning on Omniglot

  title={Gaussian Prototypical Networks for Few-Shot Learning on Omniglot},
  author={Stanislav Fort},
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… 

Figures and Tables from this paper

One-Way Prototypical Networks

A new way of training prototypical few-shot models for just a single class is shown, and a novel Gaussian layer for distance calculation in a prototypical network is proposed, which takes the support examples' distribution rather than just their centroid into account.

Kernel Relative-prototype Spectral Filtering for Few-shot Learning

This paper proposes a framework of spectral filtering (shrinkage) for measuring the difference between query samples and prototypes, or namely the relative prototypes, in a reproducing kernel Hilbert space (RKHS).

Prototypical Siamese Networks for Few-shot Learning

  • Junhua WangYongping Zhai
  • Computer Science
    2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)
  • 2020
We propose a novel architecture, called Prototypical Siamese Networks, for few-shot learning, where a classifier must generalize to new classes not seen in the training set, given only a few examples

Improved Few-Shot Visual Classification

The hypothesis that a simple class-covariance-based distance metric, namely the Mahalanobis distance, adopted into a state of the art few-shot learning approach (CNAPS) can, in and of itself, lead to a significant performance improvement is explored.

Multiclass triplet metric-learning network combined with feature mixing block for few shot learning

A multiclass triplet metric-learning network combined with a simple foreground–background feature mixing block that learns a feature embedding function that could bring similar samples close to each other and keep samples of different classes far apart to promote few-shot learning.

L2-norm prototypical networks for tackling the data shift problem in scene classification

This study presents a metric-based few-shot classification method with -norm prototypical networks that applies -norm operations to prototypes and query features to mitigate the length fluctuations caused by the data shift problem.

Prototypical Region Proposal Networks for Few-Shot Localization and Classification

A framework to unify the two stages (segmentation and classification) into an end-to-end classification model— PRoPnet—is developed and empirically demonstrate that the methods improve accuracy on image datasets with natural scenes containing multiple object classes.

Looking back to lower-level information in few-shot learning

This work proposes the utilization of lower-level, supporting information, namely the feature embeddings of the hidden neural network layers, to improve classifier accuracy and develops a method called Looking-Back, where such lower- level information is used to construct additional graphs for label propagation in limited data settings.

Gaussian Prototype Rectification For Few-shot Image Recognition

To the best of the knowledge, this paper is the first to give the theoretical derivation of Kalman data fusion for few-shot scenario and outperforms previous methods on many benchmark datasets under various settings.

Comparative Analysis on Classical Meta-Metric Models for Few-Shot Learning

The experimental results show that for all models evaluated, the addition of non-pretrained networks will make the classification results worse, which shows that it is easy to overfit when using deep networks for few-shot learning.



Prototypical Networks for Few-shot Learning

This work proposes Prototypical Networks for few-shot classification, and provides an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning.

Siamese Neural Networks for One-Shot Image Recognition

A method for learning siamese neural networks which employ a unique structure to naturally rank similarity between inputs and is able to achieve strong results which exceed those of other deep learning models with near state-of-the-art performance on one-shot classification tasks.

Matching Networks for One Shot Learning

This work employs ideas from metric learning based on deep neural features and from recent advances that augment neural networks with external memories to learn a network that maps a small labelled support set and an unlabelled example to its label, obviating the need for fine-tuning to adapt to new class types.

Optimization as a Model for Few-Shot Learning

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning

Towards a Neural Statistician

An extension of a variational autoencoder that can learn a method for computing representations, or statistics, of datasets in an unsupervised fashion is demonstrated that is able to learn statistics that can be used for clustering datasets, transferring generative models to new datasets, selecting representative samples of datasets and classifying previously unseen classes.

One-shot Learning with Memory-Augmented Neural Networks

The ability of a memory-augmented neural network to rapidly assimilate new data, and leverage this data to make accurate predictions after only a few samples is demonstrated.

One shot learning of simple visual concepts

A generative model of how characters are composed from strokes is introduced, where knowledge from previous characters helps to infer the latent strokes in novel characters, using a massive new dataset of handwritten characters.

Meta-Learning with Temporal Convolutions

This work proposes a class of simple and generic meta-learner architectures, based on temporal convolutions, that is domain- agnostic and has no particular strategy or algorithm encoded into it and outperforms state-of-the-art methods that are less general and more complex.

Meta Networks

A novel meta learning method, Meta Networks (MetaNet), is introduced that learns a meta-level knowledge across tasks and shifts its inductive biases via fast parameterization for rapid generalization.