# Visual Concept-Metaconcept Learning

arXiv: https://arxiv.org/abs/2002.01464 · HTML: https://mlsanity.com/paper/2002.01464/

## Key facts

- Cited by 39 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 4 Feb 2020.

## Built on by (most cited first, 30 of 39)

- [Learning to Predict Visual Attributes in the Wild](https://mlsanity.com/paper/2106.09707/) (2021)
- [A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices](https://mlsanity.com/paper/2203.04571/) (2022)
- [ComPhy: Compositional Physical Reasoning of Objects and Events from Videos](https://mlsanity.com/paper/2205.01089/) (2022)
- [Concept Decomposition for Visual Exploration and Inspiration](https://mlsanity.com/paper/2305.18203/) (2023)
- [NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations](https://mlsanity.com/paper/2303.13483/) (2023)
- [Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language](https://mlsanity.com/paper/2110.15358/) (2021)
- [Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution](https://mlsanity.com/paper/2103.14230/) (2021)
- [What's Left? Concept Grounding with Logic-Enhanced Foundation Models](https://mlsanity.com/paper/2310.16035/) (2023)
- [ACRE: Abstract Causal REasoning Beyond Covariation](https://mlsanity.com/paper/2103.14232/) (2021)
- [Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning](https://mlsanity.com/paper/2111.12990/) (2021)
- [Compositional Scene Representation Learning via Reconstruction: A Survey](https://mlsanity.com/paper/2202.07135/) (2022)
- [Neuro-Symbolic AI: An Emerging Class of AI Workloads and their Characterization](https://mlsanity.com/paper/2109.06133/) (2021)
- [FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations](https://mlsanity.com/paper/2203.16639/) (2022)
- [Neuro-Symbolic Forward Reasoning](https://mlsanity.com/paper/2110.09383/) (2021)
- [Language-Informed Visual Concept Learning](https://mlsanity.com/paper/2312.03587/) (2023)
- [VGNMN: Video-grounded Neural Module Network to Video-Grounded Language Tasks](https://mlsanity.com/paper/2104.07921/) (2021)
- [Compositional Physical Reasoning of Objects and Events from Videos](https://mlsanity.com/paper/2408.02687/) (2024)
- [Building Intelligent Agents with Neuro-Symbolic Concepts](https://mlsanity.com/paper/2505.06191/) (2025)
- [Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architectures](https://mlsanity.com/paper/2401.16024/) (2024)
- [Towards Learning Abductive Reasoning using VSA Distributed Representations](https://mlsanity.com/paper/2406.19121/) (2024)
- [Naturally Supervised 3D Visual Grounding with Language-Regularized Concept Learners](https://mlsanity.com/paper/2404.19696/) (2024)
- [Neuro-Symbolic Learning: Principles and Applications in Ophthalmology](https://mlsanity.com/paper/2208.00374/) (2022)
- [KANDINSKYPatterns -- An experimental exploration environment for Pattern Analysis and Machine Intelligence](https://mlsanity.com/paper/2103.00519/) (2021)
- [Benchmarking and Enhancing Disentanglement in Concept-Residual Models](https://mlsanity.com/paper/2312.00192/) (2023)
- [Zero-Shot Classification by Logical Reasoning on Natural Language Explanations](https://mlsanity.com/paper/2211.03252/) (2022)
- [Interactive Visual Task Learning for Robots](https://mlsanity.com/paper/2312.13219/) (2023)
- [OLViT: Multi-Modal State Tracking via Attention-Based Embeddings for Video-Grounded Dialog](https://mlsanity.com/paper/2402.13146/) (2024)
- [Argumentative Reward Learning: Reasoning About Human Preferences](https://mlsanity.com/paper/2209.14010/) (2022)
- [Image Manipulation via Multi-Hop Instructions -- A New Dataset and Weakly-Supervised Neuro-Symbolic Approach](https://mlsanity.com/paper/2305.14410/) (2023)
- [Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models](https://mlsanity.com/paper/2506.06242/) (2025)

## Abstract (arXiv)

Humans reason with concepts and metaconcepts: we recognize red and green from visual input; we also understand that they describe the same property of objects (i.e., the color). In this paper, we propose the visual concept-metaconcept learner (VCML) for joint learning of concepts and metaconcepts from images and associated question-answer pairs. The key is to exploit the bidirectional connection between visual concepts and metaconcepts. Visual representations provide grounding cues for predicting relations between unseen pairs of concepts. Knowing that red and green describe the same property of objects, we generalize to the fact that cube and sphere also describe the same property of objects, since they both categorize the shape of objects. Meanwhile, knowledge about metaconcepts empowers visual concept learning from limited, noisy, and even biased data. From just a few examples of purple cubes we can understand a new color purple, which resembles the hue of the cubes instead of the shape of them. Evaluation on both synthetic and real-world datasets validates our claims.