Metraipolis › archive › dc_883ee6f15522

Towards Sparsely Annotated Open-World Object Detection — arXiv:2608.12714

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.12714
License (as archived)
CC0-1.0
Archived
2026-10-19T04:55:32.616Z
SHA-256 of the archived text
7aab5e140427fb7bf44d77e613b5799d0cadc772117ef6e9d12d73a237112127
Stable URL of this page
https://metraipolis.com/documento/dc_883ee6f15522

How to cite

Towards Sparsely Annotated Open-World Object Detection — arXiv:2608.12714 — arXiv (en), https://arxiv.org/abs/2608.12714 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_883ee6f15522 (Metraipolis archive dc_883ee6f15522, sha256 7aab5e140427fb7bf44d77e613b5799d0cadc772117ef6e9d12d73a237112127)
BibTeX
@misc{dc883ee6f15522,
  title = {Towards Sparsely Annotated Open-World Object Detection — arXiv:2608.12714},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12714},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_883ee6f15522; sha256 7aab5e140427fb7bf44d77e613b5799d0cadc772117ef6e9d12d73a237112127},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12714. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Real-world object detection operates under ambiguous supervision, where unlabeled regions may correspond to missing annotations of known objects or genuinely unknown categories. These challenges have been addressed separately in Sparsely Annotated Object Detection (SAOD) and Open-World Object Detection (OWOD). In practice, their co-occurrence remains an open problem. To address this problem, we introduce Sparsely Annotated Open-World Object Detection (SA-OWOD), a new task that jointly considers sparse supervision and the presence of unseen categories. We propose Dual-Perspective Object Discovery (DPOD), a unified framework that jointly models unlabeled known and unknown instances via two complementary mechanisms. The Known Target Recovery Module (KTRM) recovers supervision for unlabeled known instances and explicitly regularizes the feature space to separate known and unknown representations. Complementarily, the Dual-Disagreement Target Generator (DDTG) identifies reliable unknown candidates through cross-view semantic inconsistency. By integrating these modules, DPOD resolves contradictory supervision signals caused by ambiguous unlabeled regions. As a result, it prevents misclassification between known and unknown objects and stabilizes the decision boundaries. Experimental results on sparsely annotated open-world benchmarks demonstrate that the proposed method outperforms existing open-world detection methods, particularly in detecting unknown objects.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-14 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.12714 — 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 2026-10-19T04:46:30.056Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).