Gaussian Prototypical Networks for Few-Shot Learning on Omniglot

Abstract

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 constructs a direction and class dependent distance metric on the embedding space, using uncertainties of individual data points as weights. We show that Gaussian prototypical networks are a preferred architecture over vanilla prototypical networks with an equivalent number of parameters. We report state-of-the-art performance in 1-shot and 5-shot classification both in 5-way and 20-way regime (for 5-shot 5-way, we are comparable to previous state-of-the-art) on the Omniglot dataset. We explore artificially down-sampling a fraction of images in the training set, which improves our performance even further. We therefore hypothesize that Gaussian prototypical networks might perform better in less homogeneous, noisier datasets, which are commonplace in real world applications.

References in corpus (4)

• Prototypical Networks for Few-shot Learning
• A Survey on Metric Learning for Feature Vectors and Structured Data
• One-shot Learning with Memory-Augmented Neural Networks
• Towards a Neural Statistician

Cited by in corpus (11)

• Small Sample Learning in Big Data Era
• Large Margin Few-Shot Learning
• Learning to Learn Variational Semantic Memory
• Stochastic Prototype Embeddings
• Prototypical Clustering Networks for Dermatological Disease Diagnosis
• Hierarchical end-to-end autonomous navigation through few-shot waypoint detection
• MxML: Mixture of Meta-Learners for Few-Shot Classification
• Variational Metric Scaling for Metric-Based Meta-Learning
• Global Semantic Description of Objects based on Prototype Theory
• Introducing the structural bases of typicality effects in deep learning
• Prototypical Region Proposal Networks for Few-Shot Localization and Classification