Metraipolis › archive › dc_7119be38c347

WALDO: One-Shot Exemplar-Conditioned Object Detection in Cluttered Scenes — arXiv:2608.28216

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28216
License (as archived)
CC0-1.0
Archived
2026-10-17T11:33:13.563Z
SHA-256 of the archived text
e1f9b2e0819b9c92488a9a93f741f3a55bad453ec925aea7d86304957d3f8bc7
Stable URL of this page
https://metraipolis.com/documento/dc_7119be38c347

How to cite

WALDO: One-Shot Exemplar-Conditioned Object Detection in Cluttered Scenes — arXiv:2608.28216 — arXiv (en), https://arxiv.org/abs/2608.28216 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7119be38c347 (Metraipolis archive dc_7119be38c347, sha256 e1f9b2e0819b9c92488a9a93f741f3a55bad453ec925aea7d86304957d3f8bc7)
BibTeX
@misc{dc7119be38c347,
  title = {WALDO: One-Shot Exemplar-Conditioned Object Detection in Cluttered Scenes — arXiv:2608.28216},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28216},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7119be38c347; sha256 e1f9b2e0819b9c92488a9a93f741f3a55bad453ec925aea7d86304957d3f8bc7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28216. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Locating a specific object instance in a cluttered scene using a single reference image and a short description, and reporting when that instance is absent, large vision-language models usually address this task. We ask whether the same capability is available far more cheaply, from representations already learned by a world-model pretraining objective. We present WALDO, a one-shot exemplar- and language-conditioned detection head with 3.4M trainable parameters that reads frozen V-JEPA 2.1 features to jointly predict object localization and target presence, with no gradient on the backbone. Because exemplar-conditioned supervision is scarce, we synthesize training episodes from instance annotations, mining exemplars from ground-truth boxes and constructing absence cases that exclude the referenced instance while leaving same-category distractors in view. This is easy to get wrong: in the obvious implementation, crop size alone predicts the label, and a head trained on it reaches 0.9998 absence AUROC without ever consulting the exemplar, and we report the negative controls that close the shortcut. On 35 held-out cluttered scenes, WALDO achieves a 0.461 catalogue AP@50, compared to 0.306 for a prompted Grounding DINO baseline under an identical scorer. Substituting DINOv3 for V-JEPA under a matched 576-token grid drops within-category absence AUROC from 0.880 to 0.726 and instance AP@50 from 0.201 to 0.141, isolating the pretraining objective rather than input resolution as the source of the gain. Instance-level Success@1, however, reaches only 0.190 against a 0.190 category-chance floor: world-model features transfer to localization precision and absence detection but not to instance identity.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.28216 — 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 2026-10-17T11:10:05.318Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).