# A Relational Model for One-Shot Classification

Source: [A Relational Model for One-Shot Classification](<https://www.sota2.com/research/paper/68fa6b341e209131cea2cdf2>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:11:34.747Z

Authors: Arturs Polis, Alexander Ilin

Published: 2021-11-08T07:53:12.000Z

## Abstract

We show that a deep learning model with built-in relational inductive bias can bring benefits to sample-efficient learning, without relying on extensive data augmentation. The proposed one-shot classification model performs relational matching of a pair of inputs in the form of local and pairwise attention. Our approach solves perfectly the one-shot image classification Omniglot challenge. Our model exceeds human level accuracy, as well as the previous state of the art, with no data augmentation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2111.04313>)

[PDF](<https://arxiv.org/pdf/2111.04313.pdf>)