Flexible Compositional Learning of Structured Visual Concepts

• URL: http://arxiv.org/abs/2105.09848v1
• Date: Thu, 20 May 2021 15:48:05 GMT
• Title: Flexible Compositional Learning of Structured Visual Concepts
• Authors: Yanli Zhou, Brenden M. Lake
• Abstract summary: 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. 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.
• Score: 17.665938343060112
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• CoLiDR: Concept Learning using Aggregated Disentangled Representations [29.932706137805713]
  Interpretability of Deep Neural Networks using concept-based models offers a promising way to explain model behavior through human-understandable concepts. A parallel line of research focuses on disentangling the data distribution into its underlying generative factors, in turn explaining the data generation process. While both directions have received extensive attention, little work has been done on explaining concepts in terms of generative factors to unify mathematically disentangled representations and human-understandable concepts.
  arXiv  Detail & Related papers  (2024-07-27T16:55:14Z)
• Compositional diversity in visual concept learning [18.907108368038216]
  Humans leverage compositionality to efficiently learn new concepts, understanding how familiar parts can combine together to form novel objects. Here, we study how people classify and generate alien figures'' with rich relational structure. We develop a Bayesian program induction model which searches for the best programs for generating the candidate visual figures.
  arXiv  Detail & Related papers  (2023-05-30T19:30:50Z)
• Concept Decomposition for Visual Exploration and Inspiration [53.06983340652571]
  We propose a method to decompose a visual concept into different visual aspects encoded in a hierarchical tree structure. We utilize large vision-language models and their rich latent space for concept decomposition and generation.
  arXiv  Detail & Related papers  (2023-05-29T16:56:56Z)
• Vector-based Representation is the Key: A Study on Disentanglement and Compositional Generalization [77.57425909520167]
  We show that it is possible to achieve both good concept recognition and novel concept composition. We propose a method to reform the scalar-based disentanglement works to be vector-based to increase both capabilities.
  arXiv  Detail & Related papers  (2023-05-29T13:05:15Z)
• Succinct Representations for Concepts [12.134564449202708]
  Foundation models like chatGPT have demonstrated remarkable performance on various tasks. However, for many questions, they may produce false answers that look accurate. In this paper, we introduce succinct representations of concepts based on category theory.
  arXiv  Detail & Related papers  (2023-03-01T12:11:23Z)
• Learning Attention Propagation for Compositional Zero-Shot Learning [71.55375561183523]
  We propose a novel method called Compositional Attention Propagated Embedding (CAPE) CAPE learns to identify this structure and propagates knowledge between them to learn class embedding for all seen and unseen compositions. We show that our method outperforms previous baselines to set a new state-of-the-art on three publicly available benchmarks.
  arXiv  Detail & Related papers  (2022-10-20T19:44:11Z)
• Visual Superordinate Abstraction for Robust Concept Learning [80.15940996821541]
  Concept learning constructs visual representations that are connected to linguistic semantics. We ascribe the bottleneck to a failure of exploring the intrinsic semantic hierarchy of visual concepts. We propose a visual superordinate abstraction framework for explicitly modeling semantic-aware visual subspaces.
  arXiv  Detail & Related papers  (2022-05-28T14:27:38Z)
• Separating Skills and Concepts for Novel Visual Question Answering [66.46070380927372]
  Generalization to out-of-distribution data has been a problem for Visual Question Answering (VQA) models. "Skills" are visual tasks, such as counting or attribute recognition, and are applied to "concepts" mentioned in the question. We present a novel method for learning to compose skills and concepts that separates these two factors implicitly within a model.
  arXiv  Detail & Related papers  (2021-07-19T18:55:10Z)
• Concepts, Properties and an Approach for Compositional Generalization [2.0559497209595823]
  This report connects a series of our work for compositional generalization, and summarizes an approach. The approach uses architecture design and regularization to regulate information of representations. We hope this work would be helpful to clarify fundamentals of compositional generalization and lead to advance artificial intelligence.
  arXiv  Detail & Related papers  (2021-02-08T14:22:30Z)
• Learning abstract structure for drawing by efficient motor program induction [52.13961975752941]
  We develop a naturalistic drawing task to study how humans rapidly acquire structured prior knowledge. We show that people spontaneously learn abstract drawing procedures that support generalization. We propose a model of how learners can discover these reusable drawing programs.
  arXiv  Detail & Related papers  (2020-08-08T13:31:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.