Metraipolis › archive › dc_f61d00a01b53

UniCounting: Instance-Aware Proposal Consolidation for Image-Query-Free Multi-Category Counting — arXiv:2610.08379

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.08379
License (as archived): CC0-1.0
Archived: 2026-10-07T13:07:38.266Z
SHA-256 of the archived text: ae746fba7f79bb1470c561482b07496e49ce4a6b95a916dc6a026fd2313b687a
Stable URL of this page: https://metraipolis.com/documento/dc_f61d00a01b53

How to cite

UniCounting: Instance-Aware Proposal Consolidation for Image-Query-Free Multi-Category Counting — arXiv:2610.08379 — arXiv (en), https://arxiv.org/abs/2610.08379 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f61d00a01b53 (Metraipolis archive dc_f61d00a01b53, sha256 ae746fba7f79bb1470c561482b07496e49ce4a6b95a916dc6a026fd2313b687a)

BibTeX

@misc{dcf61d00a01b53,
  title = {UniCounting: Instance-Aware Proposal Consolidation for Image-Query-Free Multi-Category Counting — arXiv:2610.08379},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08379},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f61d00a01b53; sha256 ae746fba7f79bb1470c561482b07496e49ce4a6b95a916dc6a026fd2313b687a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08379. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Visual counting is commonly formulated as counting a single specified target, with a model receiving an image-specific exemplar, text query, or target category and returning a single count. We instead study fixed-vocabulary image-query-free multi-category counting. A global vocabulary is fixed for each run, and, given only an RGB image, the model predicts a complete category--count vector without being told which categories appear. We present UniCounting, which casts counting as instance-aware structural inference over an over-complete proposal set. Generic segmenters produce duplicate masks, partial views, and proposals from neighboring instances; semantic scores can name them but cannot determine which denote the same object. Frozen SAM~2.1 generates masks, while frozen DINOv2 and OpenCLIP provide relation and category features. A 3,267-parameter category-shared relation head predicts same-instance affinities from instance-mask-derived supervision. Sparse graph construction, representative selection, labeling, and background-margin admission then convert each admitted component into one count with replayable group evidence. Only the relation head is trained, without count or density-map targets. On COCO clean500, UniCounting obtains lower point-estimate vector $\ell_1$ error and absent-class false mass than calibrated OWLv2-All80, with comparable micro presence F1. Under a matched decoder, the learned relation reduces both errors relative to mask containment, mask IoU, CLIP, and DINO, while revealing a fragmentation--merge trade-off. We also report transfer diagnostics on OmniCount-sub, FSC-147, and CARPK.

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/2610.08379 — 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 2026-10-07T12:37:32.977Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).