# Computer Vision Models Show Human-Like Sensitivity to Geometric and Topological Concepts

arXiv: https://arxiv.org/abs/2505.13281 · HTML: https://mlsanity.com/paper/2505.13281/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 26 of its 50 references that are in the map.
- First posted on arXiv 19 May 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [On the Relationship between Self-Attention and Convolutional Layers](https://mlsanity.com/paper/1911.03584/) (2019)
- [Large Language Models for Mathematical Reasoning: Progresses and Challenges](https://mlsanity.com/paper/2402.00157/) (2024)
- [Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future](https://mlsanity.com/paper/2001.07092/) (2020)
- [Human alignment of neural network representations](https://mlsanity.com/paper/2211.01201/) (2022)
- [TI-POOLING: transformation-invariant pooling for feature learning in Convolutional Neural Networks](https://mlsanity.com/paper/1604.06318/) (2016)
- [HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Models](https://mlsanity.com/paper/2310.16755/) (2023)
- [Testing Relational Understanding in Text-Guided Image Generation](https://mlsanity.com/paper/2208.00005/) (2022)
- [Word Acquisition in Neural Language Models](https://mlsanity.com/paper/2110.02406/) (2021)
- [Language acquisition: do children and language models follow similar learning stages?](https://mlsanity.com/paper/2306.03586/) (2023)
- [Improving neural network representations using human similarity judgments](https://mlsanity.com/paper/2306.04507/) (2023)
- [Towards A Holistic Landscape of Situated Theory of Mind in Large Language Models](https://mlsanity.com/paper/2310.19619/) (2023)
- [Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Models](https://mlsanity.com/paper/2407.06004/) (2024)
- [Babysit A Language Model From Scratch: Interactive Language Learning by Trials and Demonstrations](https://mlsanity.com/paper/2405.13828/) (2024)
- [World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models](https://mlsanity.com/paper/2306.08685/) (2023)
- [How Well Do Deep Learning Models Capture Human Concepts? The Case of the Typicality Effect](https://mlsanity.com/paper/2405.16128/) (2024)
- [Geoclidean: Few-Shot Generalization in Euclidean Geometry](https://mlsanity.com/paper/2211.16663/) (2022)
- [Human-Like Geometric Abstraction in Large Pre-trained Neural Networks](https://mlsanity.com/paper/2402.04203/) (2024)

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

- [Computer Vision Modeling of the Development of Geometric and Numerical Concepts in Humans](https://mlsanity.com/paper/2511.15029/) (2025)
- [MindTopo: Can Foundation Models Reason in Topological Space?](https://mlsanity.com/paper/2609.11900/) (2026)

## Abstract (arXiv)

With the rapid improvement of machine learning (ML) models, cognitive scientists are increasingly asking about their alignment with how humans think. Here, we ask this question for computer vision models and human sensitivity to geometric and topological (GT) concepts. Under the core knowledge account, these concepts are innate and supported by dedicated neural circuitry. In this work, we investigate an alternative explanation, that GT concepts are learned ``for free'' through everyday interaction with the environment. We do so using computer visions models, which are trained on large image datasets. We build on prior studies to investigate the overall performance and human alignment of three classes of models -- convolutional neural networks (CNNs), transformer-based models, and vision-language models -- on an odd-one-out task testing 43 GT concepts spanning seven classes. Transformer-based models achieve the highest overall accuracy, surpassing that of young children. They also show strong alignment with children's performance, finding the same classes of concepts easy vs. difficult. By contrast, vision-language models underperform their vision-only counterparts and deviate further from human profiles, indicating that na"ive multimodality might compromise abstract geometric sensitivity. These findings support the use of computer vision models to evaluate the sufficiency of the learning account for explaining human sensitivity to GT concepts, while also suggesting that integrating linguistic and visual representations might have unpredicted deleterious consequences.