Flexible Compositional Learning of Structured Visual Concepts
Not on the map. Why?
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.
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
8 of 23 references.
References · 8
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Matching Networks for One Shot Learningcited by 2,255
- 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
- 2019RAVEN: A Dataset for Relational and Analogical Visual rEasoNingcited by 226
- 2017Building machines that adapt and compute like brainscited by 99
- 2020Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoningcited by 63
- 2019Human few-shot learning of compositional instructionscited by 47
- 2019People infer recursive visual concepts from just a few examplescited by 23
Built on by
Citing papers per year: 2022: 2.
2 papers.