Metraipolis › archive › dc_fecb404a49d3

Co-Occurrence Priors Override Visual Spatial Evidence: Understanding False Alarms in Vision-Language Models for Construction Struck-By Hazard Detection — arXiv:2611.04112

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04112
License (as archived)
CC0-1.0
Archived
2026-11-04T18:55:49.449Z
SHA-256 of the archived text
c240f1f2ec531d37a602f3f78f353a0c716f3b618a34cbda2d053277a71c0155
Stable URL of this page
https://metraipolis.com/documento/dc_fecb404a49d3

How to cite

Co-Occurrence Priors Override Visual Spatial Evidence: Understanding False Alarms in Vision-Language Models for Construction Struck-By Hazard Detection — arXiv:2611.04112 — arXiv (en), https://arxiv.org/abs/2611.04112 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fecb404a49d3 (Metraipolis archive dc_fecb404a49d3, sha256 c240f1f2ec531d37a602f3f78f353a0c716f3b618a34cbda2d053277a71c0155)
BibTeX
@misc{dcfecb404a49d3,
  title = {Co-Occurrence Priors Override Visual Spatial Evidence: Understanding False Alarms in Vision-Language Models for Construction Struck-By Hazard Detection — arXiv:2611.04112},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04112},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fecb404a49d3; sha256 c240f1f2ec531d37a602f3f78f353a0c716f3b618a34cbda2d053277a71c0155},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04112. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language models (VLMs) increasingly support construction hazard monitoring, yet their frequent false alarms remain poorly understood. This study investigates whether false struck-by hazard warnings arise from failures in object recognition, spatial relation encoding, or hazard decisions dominated by learned co-occurrence priors. We evaluated Qwen2.5-VL-7B and InternVL3.5-8B using 355 counterfactual worker-excavator scene pairs with controlled spatial proximity and worker-removal variants, combining behavioral analysis, internal representation probing, causal interventions, and decision correction. Both models recognized the entities and encoded their spatial relations (out-of-fold AUROC: 0.82 and 0.91), assigning higher hazard scores to near than far scenes in 79% and 73% of pairs. Nevertheless, 74% and 100% of far scenes were falsely classified as hazardous. Removing the worker reduced Qwen's hazard rate to 11%, while worker presence exerted 2.4- and 3.2-times greater influence on hazard scores than spatial proximity in the respective models. Attention-head interventions, neuron-level interventions, and activation steering failed to eliminate this co-occurrence bias. However, conditioning hazard decisions on the model's own spatial-relation representation improved Qwen's specificity from 0.36 to 0.58 at matched sensitivity, outperforming threshold recalibration. These findings reveal that VLM struck-by false alarms stem primarily from decision-making failures rather than deficiencies in object recognition or spatial encoding, suggesting that future efforts should prioritize conditioning hazard decisions on encoded spatial evidence rather than further improving visual recognition alone.

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/2611.04112 — 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 2026-11-04T18:35:37.519Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).