# Flexible Compositional Learning of Structured Visual Concepts

arXiv: https://arxiv.org/abs/2105.09848 · HTML: https://mlsanity.com/paper/2105.09848/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 20 May 2021.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [RAVEN: A Dataset for Relational and Analogical Visual rEasoNing](https://mlsanity.com/paper/1903.02741/) (2019)
- [Building machines that adapt and compute like brains](https://mlsanity.com/paper/1711.04203/) (2017)
- [Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning](https://mlsanity.com/paper/2010.00763/) (2020)
- [Human few-shot learning of compositional instructions](https://mlsanity.com/paper/1901.04587/) (2019)
- [People infer recursive visual concepts from just a few examples](https://mlsanity.com/paper/1904.08034/) (2019)

## Built on by (most cited first, 2 of 2)

- [A Probabilistic Generative Model of Free Categories](https://mlsanity.com/paper/2205.04545/) (2022)
- [Changes from Classical Statistics to Modern Statistics and Data Science](https://mlsanity.com/paper/2211.03756/) (2022)

## Abstract (arXiv)

Humans are highly efficient learners, with the ability to grasp the meaning of a new concept from just a few examples. Unlike popular computer vision systems, humans can flexibly leverage the compositional structure of the visual world, understanding new concepts as combinations of existing concepts. In the current paper, we study how people learn different types of visual compositions, using abstract visual forms with rich relational structure. We find that people can make meaningful compositional generalizations from just a few examples in a variety of scenarios, and we develop a Bayesian program induction model that provides a close fit to the behavioral data. Unlike past work examining special cases of compositionality, our work shows how a single computational approach can account for many distinct types of compositional generalization.