Human-Like Coarse Object Representations in Vision Models

arXiv:2602.12486v1 Announce Type: new
Abstract: 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.