Metraipolis › archive › dc_7d038d683fac

BD-HazardVLM: Probing Vision-Language Models for Latent Defensive-Driving Hazards in Bangladesh Road Scenes — arXiv:2610.20627

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.20627
License (as archived): CC0-1.0
Archived: 2026-10-16T10:24:55.575Z
SHA-256 of the archived text: 83b825e93b7c288025fa3cf3ade4f2bac4de3b7df389c2a3e1a7af3ed197c85c
Stable URL of this page: https://metraipolis.com/documento/dc_7d038d683fac

How to cite

BD-HazardVLM: Probing Vision-Language Models for Latent Defensive-Driving Hazards in Bangladesh Road Scenes — arXiv:2610.20627 — arXiv (en), https://arxiv.org/abs/2610.20627 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7d038d683fac (Metraipolis archive dc_7d038d683fac, sha256 83b825e93b7c288025fa3cf3ade4f2bac4de3b7df389c2a3e1a7af3ed197c85c)

BibTeX

@misc{dc7d038d683fac,
  title = {BD-HazardVLM: Probing Vision-Language Models for Latent Defensive-Driving Hazards in Bangladesh Road Scenes — arXiv:2610.20627},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20627},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7d038d683fac; sha256 83b825e93b7c288025fa3cf3ade4f2bac4de3b7df389c2a3e1a7af3ed197c85c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20627. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language models are increasingly used for driving-scene understanding, yet their defensive reasoning under weakly structured Global South traffic remains unclear. We introduce BD-HazardVLM, a diagnostic benchmark of 500 Bangladesh road-scene images, comprising 375 from RSUD20K and 125 from TFP-BD, annotated for hazard presence, primary hazard category, risk timing, severity, defensive actions, visible evidence, and hallucination- and Western-road-bias traps. We evaluate Qwen2.5-VL-7B, InternVL3-8B, and MiniCPM-V-4.6 using a shared zero-shot task definition and structured output schema. Binary hazard-presence accuracy ranges from 88.0 percent to 89.2 percent, essentially matching the 89.0 percent majority-class baseline. Fine-grained reasoning is substantially weaker: category accuracy remains below 40 percent, risk-timing accuracy ranges from 1.6 percent to 12.4 percent, and exact defensive-action matching remains below 2 percent. Although InternVL3-8B achieves the highest severity accuracy at 61.2 percent, it has zero recall on the 58 high-severity cases. Qwen exhibits severe category mode collapse, while all models show weak latent-hazard anticipation and near-zero self-reported trap recognition. For the evaluated models, these findings show that coarse hazard recognition does not imply reliable fine-grained defensive-driving reasoning and motivate geographically diverse safety evaluation.

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); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.20627 — 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 2026-10-16T08:48:02.824Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).