# People infer recursive visual concepts from just a few examples

arXiv: https://arxiv.org/abs/1904.08034 · HTML: https://mlsanity.com/paper/1904.08034/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2019.

## Built on by (most cited first, 23 of 23)

- ["This is my unicorn, Fluffy": Personalizing frozen vision-language representations](https://mlsanity.com/paper/2204.01694/) (2022)
- [Communicating Natural Programs to Humans and Machines](https://mlsanity.com/paper/2106.07824/) (2021)
- [PoE-World: Compositional World Modeling with Products of Programmatic Experts](https://mlsanity.com/paper/2505.10819/) (2025)
- [SEVA: Leveraging sketches to evaluate alignment between human and machine visual abstraction](https://mlsanity.com/paper/2312.03035/) (2023)
- [ANPL: Towards Natural Programming with Interactive Decomposition](https://mlsanity.com/paper/2305.18498/) (2023)
- [Exploring the hierarchical structure of human plans via program generation](https://mlsanity.com/paper/2311.18644/) (2023)
- [Mitigating belief projection in explainable artificial intelligence via Bayesian Teaching](https://mlsanity.com/paper/2102.03919/) (2021)
- [Map Induction: Compositional spatial submap learning for efficient exploration in novel environments](https://mlsanity.com/paper/2110.12301/) (2021)
- [Compositional diversity in visual concept learning](https://mlsanity.com/paper/2305.19374/) (2023)
- [Spiking Neural Networks and Bio-Inspired Supervised Deep Learning: A Survey](https://mlsanity.com/paper/2307.16235/) (2023)
- [Can Humans Do Less-Than-One-Shot Learning?](https://mlsanity.com/paper/2202.04670/) (2022)
- [Synaptic Plasticity Models and Bio-Inspired Unsupervised Deep Learning: A Survey](https://mlsanity.com/paper/2307.16236/) (2023)
- [Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning](https://mlsanity.com/paper/2204.01437/) (2022)
- [Distilling Symbolic Priors for Concept Learning into Neural Networks](https://mlsanity.com/paper/2402.07035/) (2024)
- [TurtleBench: A Visual Programming Benchmark in Turtle Geometry](https://mlsanity.com/paper/2411.00264/) (2024)
- [Biologically-inspired Semi-supervised Semantic Segmentation for Biomedical Imaging](https://mlsanity.com/paper/2412.03192/) (2024)
- [Flexible Compositional Learning of Structured Visual Concepts](https://mlsanity.com/paper/2105.09848/) (2021)
- [Explainable AI for Natural Adversarial Images](https://mlsanity.com/paper/2106.09106/) (2021)
- [Cross-Modal Few-Shot Learning: a Generative Transfer Learning Framework](https://mlsanity.com/paper/2410.10663/) (2024)
- [Cognitive maps are generative programs](https://mlsanity.com/paper/2504.20628/) (2025)
- [Building Object-based Causal Programs for Human-like Generalization](https://mlsanity.com/paper/2111.12560/) (2021)
- [A Probabilistic Generative Model of Free Categories](https://mlsanity.com/paper/2205.04545/) (2022)
- ["Stop replacing salt with sugar!'': Towards Intuitive Human-Agent Teaching](https://mlsanity.com/paper/2509.24651/) (2025)

## Abstract (arXiv)

Machine learning has made major advances in categorizing objects in images, yet the best algorithms miss important aspects of how people learn and think about categories. People can learn richer concepts from fewer examples, including causal models that explain how members of a category are formed. Here, we explore the limits of this human ability to infer causal "programs" -- latent generating processes with nontrivial algorithmic properties -- from one, two, or three visual examples. People were asked to extrapolate the programs in several ways, for both classifying and generating new examples. As a theory of these inductive abilities, we present a Bayesian program learning model that searches the space of programs for the best explanation of the observations. Although variable, people's judgments are broadly consistent with the model and inconsistent with several alternatives, including a pre-trained deep neural network for object recognition, indicating that people can learn and reason with rich algorithmic abstractions from sparse input data.