Metraipolis › archive › dc_bf59f52676f4

Generative Verification: Rethinking the Uncertainty Signal for Active Learning of Object Detection — arXiv:2609.20262

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.20262
License (as archived)
CC0-1.0
Archived
2026-10-10T05:07:53.938Z
SHA-256 of the archived text
b6d0175e87d61007bbbc3268a1a02711e8f418100ea92a29145bff6029d2ac91
Stable URL of this page
https://metraipolis.com/documento/dc_bf59f52676f4

How to cite

Generative Verification: Rethinking the Uncertainty Signal for Active Learning of Object Detection — arXiv:2609.20262 — arXiv (en), https://arxiv.org/abs/2609.20262 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf59f52676f4 (Metraipolis archive dc_bf59f52676f4, sha256 b6d0175e87d61007bbbc3268a1a02711e8f418100ea92a29145bff6029d2ac91)
BibTeX
@misc{dcbf59f52676f4,
  title = {Generative Verification: Rethinking the Uncertainty Signal for Active Learning of Object Detection — arXiv:2609.20262},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.20262},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf59f52676f4; sha256 b6d0175e87d61007bbbc3268a1a02711e8f418100ea92a29145bff6029d2ac91},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20262. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Nearly every acquisition function for active object detection shares one arrangement, in that the model being improved is also the model being interrogated. We depart from it. In generative verification an independent generative model re-derives the label of a detection from the pixels inside its predicted box, and the disagreement between the two becomes the acquisition signal. Two properties follow from the arrangement itself rather than from any tuning. A displaced box, a box on background and a correct box carrying the wrong label all yield a crop that fails verification, so the failure modes arrive already combined in one scalar and the hand-weighted classification and localization terms of existing criteria are no longer needed. And because the verifier never observes the detector confidence, confidently wrong detections score highest, although a self-derived signal reads them as uninteresting and they are the costliest to leave unlabeled. We build the verifier as a conditional diffusion model whose diffusion target is a label representation rather than an image. Its reverse process is stochastic, so repeated generations return a distribution whose concentration reports how firmly the evidence determines the label, where a classifier returns a single point estimate. On PASCAL VOC and MS-COCO the signal outperforms output-uncertainty, feature-geometry, perturbation and ensemble criteria, gaining about one mAP50 point per round on MS-COCO, with its largest margins in the early rounds where confident detector errors are most common.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.20262 — 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 2026-10-10T04:26:09.594Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).