Metraipolis › archive › dc_d453a49ccd18

RECOUNT: Reference-guided Counting with Synthetic Visual Exemplars — arXiv:2608.20621

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.20621
License (as archived)
CC0-1.0
Archived
2026-10-18T10:49:27.916Z
SHA-256 of the archived text
4ef23a3a9b3c7b0711d90c3a85d311b3eb56acf892c3bee099f4dcf67709c3be
Stable URL of this page
https://metraipolis.com/documento/dc_d453a49ccd18

How to cite

RECOUNT: Reference-guided Counting with Synthetic Visual Exemplars — arXiv:2608.20621 — arXiv (en), https://arxiv.org/abs/2608.20621 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d453a49ccd18 (Metraipolis archive dc_d453a49ccd18, sha256 4ef23a3a9b3c7b0711d90c3a85d311b3eb56acf892c3bee099f4dcf67709c3be)
BibTeX
@misc{dcd453a49ccd18,
  title = {RECOUNT: Reference-guided Counting with Synthetic Visual Exemplars — arXiv:2608.20621},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20621},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d453a49ccd18; sha256 4ef23a3a9b3c7b0711d90c3a85d311b3eb56acf892c3bee099f4dcf67709c3be},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20621. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text-guided zero-shot object counters excel at spatial localization but categorize poorly on novel or fine-grained classes: natural language is too coarse to fully specify visual identity, so they fail to separate visually similar distractors. Few-shot counters sidestep this with visual exemplars, but require manual annotations on every image. To resolve this dilemma, we introduce RECOUNT, a plug-and-play framework for image-guided zero-shot counting. Rather than specify a category with a text prompt, our key insight is to specify it visually, from a single off-scene reference image. However, we find that a lone reference image provides narrow coverage of a category's appearance and is unreliable across diverse scenes. We therefore repurpose a diffusion model as an automated contrastive data engine that expands the reference into a diverse exemplar gallery, supplying the discriminative detail that text cannot. RECOUNT preserves the class-agnostic proposals of any frozen counter and offloads categorization to a separate visual module (a frozen backbone with a lightweight head trained on this synthetic data) that matches each proposal against the target and distractor galleries. Applied to a frozen counter, RECOUNT attains the best zero-shot accuracy on both benchmarks, cutting counting error (MAE) by 55% on LookAlikes and 21% on PairTally relative to the strongest prior zero-shot counter.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-24 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.20621 — 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 2026-10-18T10:48:13.547Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).