# Attentive Recurrent Comparators

arXiv: https://arxiv.org/abs/1703.00767 · HTML: https://mlsanity.com/paper/1703.00767/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2017.

## Built on by (most cited first, 13 of 13)

- [Few-Shot Diffusion Models](https://mlsanity.com/paper/2205.15463/) (2022)
- [Learning a Prior over Intent via Meta-Inverse Reinforcement Learning](https://mlsanity.com/paper/1805.12573/) (2018)
- [Meta-learning approaches for few-shot learning: A survey of recent advances](https://mlsanity.com/paper/2303.07502/) (2023)
- [How to Train Your MAML to Excel in Few-Shot Classification](https://mlsanity.com/paper/2106.16245/) (2021)
- [Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey](https://mlsanity.com/paper/2303.08557/) (2023)
- [SMAE: Few-shot Learning for HDR Deghosting with Saturation-Aware Masked Autoencoders](https://mlsanity.com/paper/2304.06914/) (2023)
- [AGI for Agriculture](https://mlsanity.com/paper/2304.06136/) (2023)
- [Privacy-Aware Detection of Fake Identity Documents: Methodology, Benchmark, and Improved Algorithms (FakeIDet2)](https://mlsanity.com/paper/2508.11716/) (2025)
- [Learning Instance and Task-Aware Dynamic Kernels for Few Shot Learning](https://mlsanity.com/paper/2112.03494/) (2021)
- [Meta-Statistical Learning: Supervised Learning of Statistical Estimators](https://mlsanity.com/paper/2502.12088/) (2025)
- [A Relational Model for One-Shot Classification](https://mlsanity.com/paper/2111.04313/) (2021)
- [Micro-Expression Recognition Based on Attribute Information Embedding and Cross-modal Contrastive Learning](https://mlsanity.com/paper/2205.14643/) (2022)
- [Visually Grounded Speech Models for Low-resource Languages and Cognitive Modelling](https://mlsanity.com/paper/2409.02865/) (2024)

## Abstract (arXiv)

Rapid learning requires flexible representations to quickly adopt to new evidence. We develop a novel class of models called Attentive Recurrent Comparators (ARCs) that form representations of objects by cycling through them and making observations. Using the representations extracted by ARCs, we develop a way of approximating a textitdynamic representation space and use it for one-shot learning. In the task of one-shot classification on the Omniglot dataset, we achieve the state of the art performance with an error rate of 1.5%. This represents the first super-human result achieved for this task with a generic model that uses only pixel information.