Research map / Vision-language and multimodal / Human and embodied modeling
Computer Vision Modeling of the Development of Geometric and Numerical Concepts in Humans
Zekun Wang, Sashank Varma
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| train ResNet-50 longer on ImageNet (more epochs) | ResNet-50 · Odd-one-out GT concepts, Euclidean Geometry, Geometrical Figures, Metric Properties, Topology | accuracy | Improved |
| train ResNet-50 longer on ImageNet (more epochs) | ResNet-50 · Odd-one-out GT concepts, Chiral Figures, Geometric Transformations, Symmetrical Figures | accuracy | No clear effect |
| train ResNet-50 longer on ImageNet (more epochs) | ResNet-50 · Odd-one-out GT concepts, overall | accuracy correlation with human development: r = 0.50 (p < 0.01) | Improved |
| train ResNet-50 longer on ImageNet (more epochs) | ResNet-50 · Numerosity stimulus set 1, distance effect | correlation: r = 0.15 -> 0.80 | Improved |
| train ResNet-50 longer on ImageNet (more epochs) | ResNet-50 · Numerosity stimulus set 1, ratio effect | R2: 0.14 -> 0.90 | Improved |
| train ResNet-50 longer on ImageNet (more epochs) | ResNet-50 · Numerosity stimulus set 1, size effect | correlation: r = 0.09 -> 0.32 | Mixed |
| use more varied stimulus sets (5 and 6) (ablation) | ResNet-50 number representation · Numerosity stimulus sets 5 and 6 | ratio effect R2 | Hurt |
Closest papers by meaning
- Alignment of CNN and Human Judgments of Geometric and Topological Concepts (AAAI 2025 · similarity 0.92)
- Evaluating alignment between humans and neural network representations in image-based learning tasks (NeurIPS 2024 · similarity 0.86)
- Evaluating Large Vision-and-Language Models on Children's Mathematical Olympiads (NeurIPS 2024 · similarity 0.85)
- KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Models (ICLR 2025 · similarity 0.85)
- Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests (NeurIPS 2026 · similarity 0.85)
- Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
