Metraipolis › archive › dc_f4948ed1f040

Industrial Anomaly Detection via Defect-Grounded Reasoning in Visual Latent Space — arXiv:2609.29457

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29457
License (as archived)
CC0-1.0
Archived
2026-10-08T06:44:29.940Z
SHA-256 of the archived text
7ef929e6d8699adf9ea7765c87eaa783342afd2dbaa8b4a9cc00f1f6151e4e5e
Stable URL of this page
https://metraipolis.com/documento/dc_f4948ed1f040

How to cite

Industrial Anomaly Detection via Defect-Grounded Reasoning in Visual Latent Space — arXiv:2609.29457 — arXiv (en), https://arxiv.org/abs/2609.29457 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f4948ed1f040 (Metraipolis archive dc_f4948ed1f040, sha256 7ef929e6d8699adf9ea7765c87eaa783342afd2dbaa8b4a9cc00f1f6151e4e5e)
BibTeX
@misc{dcf4948ed1f040,
  title = {Industrial Anomaly Detection via Defect-Grounded Reasoning in Visual Latent Space — arXiv:2609.29457},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29457},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f4948ed1f040; sha256 7ef929e6d8699adf9ea7765c87eaa783342afd2dbaa8b4a9cc00f1f6151e4e5e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29457. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Industrial anomaly detection (IAD) is evolving beyond conventional detection and localization toward multimodal inspection systems that can describe, explain, and reason about fine-grained defects. Although recent multimodal large language model (MLLM)-based methods improve anomaly understanding through textual reasoning and visual guidance, they face two limitations in fine-grained inspection. First, their visual refinement often requires iteratively revisiting local image regions or augmenting with additional tools. Second, the resulting local defect evidence may not be reliably preserved throughout subsequent reasoning. To address these, we propose Anomaly-LR, a defect-grounded latent reasoning framework that first forms a global understanding of the input and then progressively refines anomaly-relevant representations directly in the visual latent space. We further construct IAD-LR-22K, the first IAD instruction dataset designed for latent reasoning, containing 22,228 image-question instances from 4,523 industrial images, with global textual reasoning traces and region-level visual annotations. Extensive experiments show that Anomaly-LR achieves state-of-the-art performance among comparable-scale methods across multiple IAD benchmarks, without requiring external references or tools. The code and data will be released at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.29457 — 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 2026-10-08T06:09:29.855Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).