Metraipolis › archive › dc_6c9bee197cf7

Beyond Balanced Accuracy: A Resolution and Parity-Controlled Benchmark for Vision-Language and Vision-Only Defect Assessment in UAV Power-Line Inspection — arXiv:2609.27457

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27457
License (as archived)
CC0-1.0
Archived
2026-10-08T12:34:50.472Z
SHA-256 of the archived text
1d473dc3623553002babb5b292c53e4328095d7936751c7cf231c3819dfbbd5e
Stable URL of this page
https://metraipolis.com/documento/dc_6c9bee197cf7

How to cite

Beyond Balanced Accuracy: A Resolution and Parity-Controlled Benchmark for Vision-Language and Vision-Only Defect Assessment in UAV Power-Line Inspection — arXiv:2609.27457 — arXiv (en), https://arxiv.org/abs/2609.27457 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6c9bee197cf7 (Metraipolis archive dc_6c9bee197cf7, sha256 1d473dc3623553002babb5b292c53e4328095d7936751c7cf231c3819dfbbd5e)
BibTeX
@misc{dc6c9bee197cf7,
  title = {Beyond Balanced Accuracy: A Resolution and Parity-Controlled Benchmark for Vision-Language and Vision-Only Defect Assessment in UAV Power-Line Inspection — arXiv:2609.27457},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27457},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6c9bee197cf7; sha256 1d473dc3623553002babb5b292c53e4328095d7936751c7cf231c3819dfbbd5e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27457. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language models (VLMs) are often reported to outperform task-specific vision backbones for unmanned aerial vehicle (UAV) power-line defect assessment. We test that claim on ElecVQA-Bench, a 56,972-item benchmark derived from the public InsPLAD dataset, across six evaluation choices: partition, evaluated item set, label space, replication, input resolution, and side information. On a matched partition, a Swin Transformer and the strongest adapted VLM differ by only 0.03 points at binary screening. At seven-way defect typing, increasing the vision backbones from 224 px to the measured pixel budget of the VLM preprocessor narrows the gap against InternVL3.5-8B from +20.53 to -0.57 points for ResNet-50 and from +23.67 to +4.70 points for Swin-T. A pixel-budget audit shifts Qwen3-VL-8B macro recall by 10.78 points, yet a source-pixel-matched InternVL control still leaves Qwen ahead by 7.43 to 13.61 points while using 56% fewer visual tokens, so neither source pixels nor token budget explains the difference between the two VLMs. A two-seed global replication changes Qwen binary accuracy and seven-way macro recall by 0.86 and 1.02 points. After split-specific retraining, Qwen does not lead at crop or image level, and a 14-tower, three-seed replication reverses the sign across seeds, giving mean common-six macro recall of 0.9085 for Qwen against 0.9509 for ResNet-50. No split regime yields a family-level advantage that survives multiple-comparison correction. The study supports a benchmark-audit contribution rather than a general claim of VLM superiority.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.27457 — 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 2026-10-08T12:12:35.680Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).