# One-Way Prototypical Networks

arXiv: https://arxiv.org/abs/1906.00820 · HTML: https://mlsanity.com/paper/1906.00820/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2019.

## Built on by (most cited first, 5 of 5)

- [A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detection](https://mlsanity.com/paper/2104.14535/) (2021)
- [Zero-Shot Anomaly Detection via Batch Normalization](https://mlsanity.com/paper/2302.07849/) (2023)
- [Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection](https://mlsanity.com/paper/2103.00684/) (2021)
- [Classical Sequence Match is a Competitive Few-Shot One-Class Learner](https://mlsanity.com/paper/2209.06394/) (2022)
- [Few-Shot Learning for Industrial Time Series: A Comparative Analysis Using the Example of Screw-Fastening Process Monitoring](https://mlsanity.com/paper/2506.13909/) (2025)

## Abstract (arXiv)

Few-shot models have become a popular topic of research in the past years. They offer the possibility to determine class belongings for unseen examples using just a handful of examples for each class. Such models are trained on a wide range of classes and their respective examples, learning a decision metric in the process. Types of few-shot models include matching networks and prototypical networks. We show a new way of training prototypical few-shot models for just a single class. These models have the ability to predict the likelihood of an unseen query belonging to a group of examples without any given counterexamples. The difficulty here lies in the fact that no relative distance to other classes can be calculated via softmax. We solve this problem by introducing a "null class" centered around zero, and enforcing centering with batch normalization. Trained on the commonly used Omniglot data set, we obtain a classification accuracy of .98 on the matched test set, and of .8 on unmatched MNIST data. On the more complex MiniImageNet data set, test accuracy is .8. In addition, we propose a novel Gaussian layer for distance calculation in a prototypical network, which takes the support examples' distribution rather than just their centroid into account. This extension shows promising results when a higher number of support examples is available.