Metraipolis › archive › dc_21e71683eaab
More Accurate, Less Human: Gestalt Grouping in Vision Models — arXiv:2608.10195
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10195
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:19:41.085Z
- SHA-256 of the archived text
2944af55e540b57795555880ca186c9c55beab25c0eb039470f8ed77b74935a8- Stable URL of this page
https://metraipolis.com/documento/dc_21e71683eaab
How to cite
More Accurate, Less Human: Gestalt Grouping in Vision Models — arXiv:2608.10195 — arXiv (en), https://arxiv.org/abs/2608.10195 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_21e71683eaab (Metraipolis archive dc_21e71683eaab, sha256 2944af55e540b57795555880ca186c9c55beab25c0eb039470f8ed77b74935a8)
BibTeX
@misc{dc21e71683eaab,
title = {More Accurate, Less Human: Gestalt Grouping in Vision Models — arXiv:2608.10195},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10195},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_21e71683eaab; sha256 2944af55e540b57795555880ca186c9c55beab25c0eb039470f8ed77b74935a8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10195. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Human vision organizes what it sees into wholes: same-colored points group into series, similar marks cohere into categories, and shapes complete into recognizable objects. These are the Gestalt operations that visualization design builds on. Whether vision models organize visual content this way has not been systematically tested. We introduce a behavioral battery that scores models against human data from prior perception studies on four grouping tasks: mark-color odd-one-out, color-series counting, silhouette recognition, and object odd-one-out. We apply it to 45 models across five training families: supervised, self-supervised, and contrastive vision-language encoders, open-weight VLMs, and closed foundation models. The battery reveals that agreement with human responses captures aspects of perceptual organization that conventional performance metrics fail to distinguish, with several closed models exhibiting substantially lower alignment than their benchmark accuracy would suggest. Scoring against published perception data therefore gives visualization research a reusable yardstick, requiring no new user study, for auditing whether the models now entering visualization pipelines organize what they see the way their human audience does. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.10195 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T06:11:45.124Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).