Saved in:
Bibliographic Details
Main Authors: Gizdov, Andrey, Procopio, Andrea, Li, Yichen, Harari, Daniel, Ullman, Tomer
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.12486
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917272216403968
author Gizdov, Andrey
Procopio, Andrea
Li, Yichen
Harari, Daniel
Ullman, Tomer
author_facet Gizdov, Andrey
Procopio, Andrea
Li, Yichen
Harari, Daniel
Ullman, Tomer
contents Humans appear to represent objects for intuitive physics with coarse, volumetric bodies'' that smooth concavities - trading fine visual details for efficient physical predictions - yet their internal structure is largely unknown. Segmentation models, in contrast, optimize pixel-accurate masks that may misalign with such bodies. We ask whether and when these models nonetheless acquire human-like bodies. Using a time-to-collision (TTC) behavioral paradigm, we introduce a comparison pipeline and alignment metric, then vary model training time, size, and effective capacity via pruning. Across all manipulations, alignment with human behavior follows an inverse U-shaped curve: small/briefly trained/pruned models under-segment into blobs; large/fully trained models over-segment with boundary wiggles; and an intermediate ideal body granularity'' best matches humans. This suggests human-like coarse bodies emerge from resource constraints rather than bespoke biases, and points to simple knobs - early checkpoints, modest architectures, light pruning - for eliciting physics-efficient representations. We situate these results within resource-rational accounts balancing recognition detail against physical affordances.
format Preprint
id arxiv_https___arxiv_org_abs_2602_12486
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Human-Like Coarse Object Representations in Vision Models
Gizdov, Andrey
Procopio, Andrea
Li, Yichen
Harari, Daniel
Ullman, Tomer
Computer Vision and Pattern Recognition
Artificial Intelligence
Humans appear to represent objects for intuitive physics with coarse, volumetric bodies'' that smooth concavities - trading fine visual details for efficient physical predictions - yet their internal structure is largely unknown. Segmentation models, in contrast, optimize pixel-accurate masks that may misalign with such bodies. We ask whether and when these models nonetheless acquire human-like bodies. Using a time-to-collision (TTC) behavioral paradigm, we introduce a comparison pipeline and alignment metric, then vary model training time, size, and effective capacity via pruning. Across all manipulations, alignment with human behavior follows an inverse U-shaped curve: small/briefly trained/pruned models under-segment into blobs; large/fully trained models over-segment with boundary wiggles; and an intermediate ideal body granularity'' best matches humans. This suggests human-like coarse bodies emerge from resource constraints rather than bespoke biases, and points to simple knobs - early checkpoints, modest architectures, light pruning - for eliciting physics-efficient representations. We situate these results within resource-rational accounts balancing recognition detail against physical affordances.
title Human-Like Coarse Object Representations in Vision Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2602.12486