# Gaussian Prototypical Networks for Few-Shot Learning on Omniglot

arXiv: https://arxiv.org/abs/1708.02735 · HTML: https://mlsanity.com/paper/1708.02735/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2017.

## Built on by (most cited first, 20 of 20)

- [von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning](https://mlsanity.com/paper/2103.15718/) (2021)
- [Meta-learning approaches for few-shot learning: A survey of recent advances](https://mlsanity.com/paper/2303.07502/) (2023)
- [Prototypical Reward Network for Data-Efficient RLHF](https://mlsanity.com/paper/2406.06606/) (2024)
- [Circumpapillary OCT-Focused Hybrid Learning for Glaucoma Grading Using Tailored Prototypical Neural Networks](https://mlsanity.com/paper/2106.13551/) (2021)
- [Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning](https://mlsanity.com/paper/2201.05151/) (2022)
- [On the cross-lingual transferability of multilingual prototypical models across NLU tasks](https://mlsanity.com/paper/2207.09157/) (2022)
- [Kernel Relative-prototype Spectral Filtering for Few-shot Learning](https://mlsanity.com/paper/2207.11685/) (2022)
- [Hierarchical end-to-end autonomous navigation through few-shot waypoint detection](https://mlsanity.com/paper/2409.14633/) (2024)
- [Offline Handwritten Amharic Character Recognition Using Few-shot Learning](https://mlsanity.com/paper/2210.00275/) (2022)
- [Embedding Generalized Semantic Knowledge into Few-Shot Remote Sensing Segmentation](https://mlsanity.com/paper/2405.13686/) (2024)
- [Trajectory-aware Principal Manifold Framework for Data Augmentation and Image Generation](https://mlsanity.com/paper/2310.07801/) (2023)
- [Few-Shot Learning of Visual Compositional Concepts through Probabilistic Schema Induction](https://mlsanity.com/paper/2505.09859/) (2025)
- [Prototypical Region Proposal Networks for Few-Shot Localization and Classification](https://mlsanity.com/paper/2104.03496/) (2021)
- [Introducing the structural bases of typicality effects in deep learning](https://mlsanity.com/paper/2107.03279/) (2021)
- [SENet: A Spectral Filtering Approach to Represent Exemplars for Few-shot Learning](https://mlsanity.com/paper/2305.18970/) (2023)
- [Potential Energy based Mixture Model for Noisy Label Learning](https://mlsanity.com/paper/2405.01186/) (2024)
- [Like Humans to Few-Shot Learning through Knowledge Permeation of Vision and Text](https://mlsanity.com/paper/2405.12543/) (2024)
- [ProtoTopic: Prototypical Network for Few-Shot Medical Topic Modeling](https://mlsanity.com/paper/2510.13542/) (2025)
- [TCLA: Training-Free Class-wise Logit Adaptation for Medical Vision-Language Models](https://mlsanity.com/paper/2607.09562/) (2026)
- [Learned Enterprise Data Comprehension: Compression and Routing for Data Agents](https://mlsanity.com/paper/2609.25286/) (2026)

## Abstract (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 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.