Metraipolis › archive › dc_d61ddb08fc88

A Patch is More Than a Token — arXiv:2610.41814

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41814
License (as archived)
CC0-1.0
Archived
2026-11-02T05:03:48.867Z
SHA-256 of the archived text
c6b77adba4a80ff1e91bc8a41825269168c6230f12045e6a90c27d9bd30d718d
Stable URL of this page
https://metraipolis.com/documento/dc_d61ddb08fc88

How to cite

A Patch is More Than a Token — arXiv:2610.41814 — arXiv (en), https://arxiv.org/abs/2610.41814 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d61ddb08fc88 (Metraipolis archive dc_d61ddb08fc88, sha256 c6b77adba4a80ff1e91bc8a41825269168c6230f12045e6a90c27d9bd30d718d)
BibTeX
@misc{dcd61ddb08fc88,
  title = {A Patch is More Than a Token — arXiv:2610.41814},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41814},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d61ddb08fc88; sha256 c6b77adba4a80ff1e91bc8a41825269168c6230f12045e6a90c27d9bd30d718d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41814. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision Transformers represent each image patch through a canonical token produced under one observation condition. That token is a powerful interface, but it is still one realized state of the patch. We introduce PMTT, which establishes two foundations: a patch representation object can extend from one canonical state to a canonical-centered Representation State Family, and identity-preserving variation opens Patch-Level Local Feature Space. We develop four parts of this representation program. Patch Information Acquisition and Dense Orbital Views expose lawful same-patch states. Visible-to-Hidden prediction tests whether observed states reveal structure beyond themselves. Intrinsic analysis identifies low-dimensional, energy-concentrated, patch-specific, predictive geometry. Representation Organization separates acquiring more information from organizing that information, with an analytic Manifold as the central structured representation. We realize PMTT on frozen DINOv3 S/B/L/H+ backbones without neural post-training of the representation. Across two independent 4,096-anchor cohorts, Manifold explains 70.8-79.6% of Hidden variation, compared with 55.0-72.3% for directly Observed states, and wins on more than 95% of anchors at every scale. Effective rank falls from about 2.5 to 2.0 while dominant energy concentration rises with backbone scale. Across six visual capabilities and four scales, Observed exceeds the canonical Center in 21 of 24 conditions, Manifold exceeds Center in 23, and Manifold exceeds Observed in 16. The strongest current consequence appears in physical correspondence, where MegaDepth satisfies Center < Observed < Manifold at every scale. These results show that pretrained visual backbones contain richer patch information than the standard single-token interface directly exposes. Code and experimental assets are available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.41814 — 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 2026-11-02T04:49:13.274Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).