Research map / Detection and segmentation / Open-set and few-shot detection
Do Computational Models Differ Systematically From Human Object Perception?
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Fit the CNN's 100 principal-component features to human dissimilarity data | CNN (VGG-16) · Human perceived object dissimilarity | explainable variance explained: 55.1% -> 62.6% | Helped |
| Combine the distances from 19 models using a weighted sum | Computational models of object perception · Human perceived object dissimilarity | explainable variance explained: 62.6% -> 68.1% | Helped |
| Use image pairs with greater symmetry | Computational models compared with human perception · Object-pair dissimilarity | residual error (observed minus predicted) | Hurt |
| Use image pairs with a larger object-area ratio | Individual computational models compared with human perception · Object-pair dissimilarity | residual error (observed minus predicted) | Hurt |
| Use object pairs that share parts or other features | Computational models compared with human perception · Object-pair dissimilarity | residual error (observed minus predicted) | Mixed |
Closest papers by meaning
- Evaluating Multiview Object Consistency in Humans and Image Models (NeurIPS 2024 · similarity 0.87)
- Contour Integration Underlies Human-Like Vision (ICML 2025 · similarity 0.86)
- Human and AI Perceptual Differences in Image Classification Errors (AAAI 2025 · similarity 0.86)
- Characterizing Universal Object Representations Across Vision Models (NeurIPS 2026 · similarity 0.85)
- When does perceptual alignment benefit vision representations? (NeurIPS 2024 · similarity 0.85)
- Evaluating alignment between humans and neural network representations in image-based learning tasks (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.