# Learning from One and Only One Shot

arXiv: https://arxiv.org/abs/2201.08815 · HTML: https://mlsanity.com/paper/2201.08815/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 48 references that are in the map.
- First posted on arXiv 14 Jan 2022.

## Builds on (most cited first, 12 of 12)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Geometric deep learning: going beyond Euclidean data](https://mlsanity.com/paper/1611.08097/) (2016)
- [Big Transfer (BiT): General Visual Representation Learning](https://mlsanity.com/paper/1912.11370/) (2019)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Fast Computation of Wasserstein Barycenters](https://mlsanity.com/paper/1310.4375/) (2013)
- [EMNIST: an extension of MNIST to handwritten letters](https://mlsanity.com/paper/1702.05373/) (2017)
- [Unsupervised Learning via Meta-Learning](https://mlsanity.com/paper/1810.02334/) (2018)
- [Doodle to Search: Practical Zero-Shot Sketch-based Image Retrieval](https://mlsanity.com/paper/1904.03451/) (2019)
- [The Omniglot challenge: a 3-year progress report](https://mlsanity.com/paper/1902.03477/) (2019)
- [TextCaps : Handwritten Character Recognition with Very Small Datasets](https://mlsanity.com/paper/1904.08095/) (2019)
- [One-Shot Learning using Mixture of Variational Autoencoders: a Generalization Learning approach](https://mlsanity.com/paper/1804.07645/) (2018)

## Built on by (most cited first, 4 of 4)

- [SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs](https://mlsanity.com/paper/2604.07737/) (2026)
- [Advancing site-specific disease and pest management in precision agriculture: From reasoning-driven foundation models to adaptive, feedback-based learning](https://mlsanity.com/paper/2510.24650/) (2025)
- [Information Lattice Learning as Probabilistic Graphical Model Structure Learning](https://mlsanity.com/paper/2606.19366/) (2026)
- [Hidden-Shot: Towards One-Shot Task Generalization for Low-Level Vision Generalist Models](https://mlsanity.com/paper/2607.01535/) (2026)

## Abstract (arXiv)

Humans can generalize from only a few examples and from little pretraining on similar tasks. Yet, machine learning (ML) typically requires large data to learn or pre-learn to transfer. Motivated by nativism and artificial general intelligence, we directly model human-innate priors in abstract visual tasks such as character and doodle recognition. This yields a white-box model that learns general-appearance similarity by mimicking how humans naturally ``distort'' an object at first sight. Using just nearest-neighbor classification on this cognitively-inspired similarity space, we achieve human-level recognition with only 1--10 examples per class and no pretraining. This differs from few-shot learning that uses massive pretraining. In the tiny-data regime of MNIST, EMNIST, Omniglot, and QuickDraw benchmarks, we outperform both modern neural networks and classical ML. For unsupervised learning, by learning the non-Euclidean, general-appearance similarity space in a k-means style, we achieve multifarious visual realizations of abstract concepts by generating human-intuitive archetypes as cluster centroids.