Authors
Ono, H., Yamashita, A., Amano, K., Sawayama, M.
Abstract
Human-like behavior in visual models does not necessarily imply human-like internal computation. When a model recognizes objects robustly across changes in visual style, what internal computations support this behavior, and which are relevant to human perception? We addressed this question by pruning style-robust neural networks into candidate submodels corresponding to two computational strategies. The first retained channels whose responses were stable across style changes for fixed content, yielding a Content Stability Score (CSS)-based submodel. The second retained channels whose responses were stable across content changes for fixed style, yielding a Style Stability Score (SSS)-based submodel. Across ImageNet, Stylized ImageNet, and model-versus-human benchmarks, the two submodel families showed comparable object-recognition performance. We then used their exclusive feature subspaces to generate matched images with Gram-matrix-based neural style transfer and asked human observers which image was more similar in visual style to a reference image. Images generated from the CSS-based submodel were selected significantly more often than chance, even though CSS preferentially retained channels whose individual activation patterns were relatively insensitive to style. These results suggest that representations preserving content across style changes are more consistent with human judgments of visual style. More broadly, they demonstrate a framework for isolating candidate computational subspaces from large artificial models and testing their perceptual relevance through image synthesis.
Preprint server:
bioRxiv
The authors list and abstract were imported from bioRxiv on 27 Oct 2026.
Advertisement
Stats
- Recommendations n/a n/a positive of 0 vote(s)
- Views 6
- Comments 0