Metraipolis › archive › dc_44c444091c88

DROA-CLIPSeg: Prompt-Guided Thin Crack Segmentation in Low-Light Conditions — arXiv:2610.33635

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.33635
License (as archived)
CC0-1.0
Archived
2026-10-27T08:00:22.559Z
SHA-256 of the archived text
803629ddaefcb9c304742708dd23d0e16c9498da08d099bdb4dea68c7f5b21c8
Stable URL of this page
https://metraipolis.com/documento/dc_44c444091c88

How to cite

DROA-CLIPSeg: Prompt-Guided Thin Crack Segmentation in Low-Light Conditions — arXiv:2610.33635 — arXiv (en), https://arxiv.org/abs/2610.33635 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_44c444091c88 (Metraipolis archive dc_44c444091c88, sha256 803629ddaefcb9c304742708dd23d0e16c9498da08d099bdb4dea68c7f5b21c8)
BibTeX
@misc{dc44c444091c88,
  title = {DROA-CLIPSeg: Prompt-Guided Thin Crack Segmentation in Low-Light Conditions — arXiv:2610.33635},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33635},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_44c444091c88; sha256 803629ddaefcb9c304742708dd23d0e16c9498da08d099bdb4dea68c7f5b21c8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33635. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pavement crack segmentation under low light is degraded by reduced contrast, shadows, headlight glare, joints, stains, and wet seams. Existing crack segmentation methods mostly assume good illumination. Low-light enhancement methods improve visual quality, but they do not explicitly preserve crack topology. To address these limitations, we formulate low-light crack segmentation as a degradation-aware, prompt-grounded structural defect segmentation problem and propose DROA-CLIPSeg, a parameter-efficient framework that adapts a frozen CLIPSeg vision language backbone using two lightweight modules. QKV Low-Rank Adaptation is injected into the Q/K/V projections of the vision and text encoders to improve crack-specific image text alignment without backbone fine-tuning. The proposed Domain Residual Orthogonal Adapter (DROA) decomposes intermediate features into a dominant crack-domain branch, which captures recurring low-light crack patterns, and an orthogonal residual branch, which preserves faint, thin, and fragmented evidence usually suppressed by noise, shadow, or over-smoothing. We also introduce CrackLingo-9K and CrackLingo-12K, text augmented versions of Crack9k and Crack12k with crack-aware prompts. Training only approximately 1.93 M parameters, corresponding to 1.3% of the full model, DROA-CLIPSeg outperforms 9 zero-shot and 4 fine-tuned vision language baselines on both splits, generalises zero-shot to MVTec AD across textures and defect morphologies, and is supported by extensive ablations. Our source code is publicly available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.33635 — 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 2026-10-27T07:55:30.838Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).