Metraipolis › archive › dc_348cbb0973aa

Shifting Focus by Reliability: Geometric Fusion Modulation for Robust RGB-T Detection — arXiv:2610.41204

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41204
License (as archived): CC0-1.0
Archived: 2026-11-03T05:41:25.705Z
SHA-256 of the archived text: aa377c9ed362d2a845559fe3d77db71e9571fd33eaa524d85dafa40c73b87fcf
Stable URL of this page: https://metraipolis.com/documento/dc_348cbb0973aa

How to cite

Shifting Focus by Reliability: Geometric Fusion Modulation for Robust RGB-T Detection — arXiv:2610.41204 — arXiv (en), https://arxiv.org/abs/2610.41204 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_348cbb0973aa (Metraipolis archive dc_348cbb0973aa, sha256 aa377c9ed362d2a845559fe3d77db71e9571fd33eaa524d85dafa40c73b87fcf)

BibTeX

@misc{dc348cbb0973aa,
  title = {Shifting Focus by Reliability: Geometric Fusion Modulation for Robust RGB-T Detection — arXiv:2610.41204},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41204},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_348cbb0973aa; sha256 aa377c9ed362d2a845559fe3d77db71e9571fd33eaa524d85dafa40c73b87fcf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41204. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

RGB-thermal (RGB-T) object detectors combine visible and thermal imagery for robust detection, but signal corruption in either stream can substantially degrade accuracy. Restoration-based methods incur significant latency and do not consistently improve downstream accuracy, raising a more direct question: rather than restoring corrupted inputs, can we efficiently adapt the detector to their varying signal quality? Conventional PEFT offers an efficient route, but its input-independent corrections cannot track diverse test-time corruptions. Our controlled corruption sweeps show that corruption types have similar effects near clean conditions but diverge increasingly with severity, motivating corruption-aware, per-input adaptation. We therefore propose PG-FM (Prompt-Guided Feature Modulation), which adapts RGB-T object detectors to the estimated corruption type and severity of each modality. Under controlled RGB-T corruption simulations, PG-FM preserves clean-set performance, improves mAP50 by up to 20.8 points on FLIR and 19.9 points on KAIST, and transfers without retraining to unmodified, naturally acquired external RGB-T datasets.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.41204 — 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 2026-11-03T05:26:25.983Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).