Metraipolis › archive › dc_30f17c59c2e2

FM-ReID: Selective Competitive Token Routing for Object Re-Identification — arXiv:2609.36560

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36560
License (as archived)
CC0-1.0
Archived
2026-10-07T16:26:04.739Z
SHA-256 of the archived text
039ad383c5bf9b0fc1ae38cf7eecb580604c3cff0fac93263f60b1f04a3e7d2e
Stable URL of this page
https://metraipolis.com/documento/dc_30f17c59c2e2

How to cite

FM-ReID: Selective Competitive Token Routing for Object Re-Identification — arXiv:2609.36560 — arXiv (en), https://arxiv.org/abs/2609.36560 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_30f17c59c2e2 (Metraipolis archive dc_30f17c59c2e2, sha256 039ad383c5bf9b0fc1ae38cf7eecb580604c3cff0fac93263f60b1f04a3e7d2e)
BibTeX
@misc{dc30f17c59c2e2,
  title = {FM-ReID: Selective Competitive Token Routing for Object Re-Identification — arXiv:2609.36560},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36560},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_30f17c59c2e2; sha256 039ad383c5bf9b0fc1ae38cf7eecb580604c3cff0fac93263f60b1f04a3e7d2e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36560. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Object re-identification (ReID) faces a recurring challenge: different identities can share highly similar global appearances, while the cues that distinguish them are localized, heterogeneous, and visible only under particular viewpoints. This challenge arises in animal ReID through markings, contours, and scars, in person ReID through subtle clothing and accessory cues, and in vehicle ReID through localized appearance details. Although visual foundation models encode such information in dense tokens, a single holistic descriptor can obscure discriminative local signals. We propose FM-ReID, an end-to-end framework that formulates local representation learning as selective competitive token routing. Its Competitive Fine-grained Mining module uses multiple mining queries and a residual query to compete for dense DINOv3 tokens. Above-prior selection retains tokens preferentially allocated to each mining query, while the residual slot receives tokens excluded from the retrieval descriptors. The resulting multi-query descriptors are jointly trained with a holistic representation for retrieval, without fixed spatial partitions or equal-area constraints. FM-ReID achieves strong results on animal, person, and vehicle ReID benchmarks, supporting competitive token routing as an effective way to augment holistic foundation-model representations.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.36560 — 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 2026-10-07T15:54:53.860Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).