Metraipolis › archive › dc_bca15f54bb2c

Hyperbolic Geometry for Open-World Object Detection in Remote Sensing Imagery — arXiv:2609.09626

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.09626
License (as archived)
CC0-1.0
Archived
2026-10-16T07:26:01.768Z
SHA-256 of the archived text
65d114ffea6a6fbbc47197093fb9a33922df7c5a34a13810436ee9298a54a690
Stable URL of this page
https://metraipolis.com/documento/dc_bca15f54bb2c

How to cite

Hyperbolic Geometry for Open-World Object Detection in Remote Sensing Imagery — arXiv:2609.09626 — arXiv (en), https://arxiv.org/abs/2609.09626 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bca15f54bb2c (Metraipolis archive dc_bca15f54bb2c, sha256 65d114ffea6a6fbbc47197093fb9a33922df7c5a34a13810436ee9298a54a690)
BibTeX
@misc{dcbca15f54bb2c,
  title = {Hyperbolic Geometry for Open-World Object Detection in Remote Sensing Imagery — arXiv:2609.09626},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09626},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bca15f54bb2c; sha256 65d114ffea6a6fbbc47197093fb9a33922df7c5a34a13810436ee9298a54a690},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09626. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Open-world object detection (OWOD) extends closed-set detection by requiring models to identify unknown objects and incrementally learn them once annotations become available. In remote sensing imagery, object categories often exhibit latent hierarchical relationships that may be inadequately represented in the Euclidean spaces commonly adopted by existing methods, limiting unknown-object recall and incremental-learning performance. To address this issue, we investigate hyperbolic geometry for OWOD in remote sensing imagery and propose HyRS-OWOD. To improve unknown object recall, we design a two-step unknown-object discovery mechanism: a Decoupled Objectness Learning (DOL) module that disentangles foreground perception from semantic information to separate foreground proposals from background regions, followed by a Hyperbolic Uncertainty Learning (HUL) component that leverages the radius of hyperbolic embeddings as an uncertainty-aware cue for known-unknown discrimination. For incremental learning, we develop a Hyperbolic Metric Learning (HML) strategy that enhances inter-class separability, facilitating the incorporation of novel categories while mitigating catastrophic forgetting. Experiments on three remote sensing benchmarks demonstrate consistent improvements in unknown recall and incremental learning over state-of-the-art OWOD methods.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.09626 — 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 2026-10-16T07:00:16.333Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).