Metraipolis › archive › dc_4166c255b20e
VD-DeepStack: Bridging Visual Comparison and Language Reasoning for Few-Shot Anomaly Detection — arXiv:2609.34949
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34949
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:58:21.732Z
- SHA-256 of the archived text
d211297ad2fe45c25a297b37ebc46477a49daee29df4ee94fb27c3d4f1987ad4- Stable URL of this page
https://metraipolis.com/documento/dc_4166c255b20e
How to cite
VD-DeepStack: Bridging Visual Comparison and Language Reasoning for Few-Shot Anomaly Detection — arXiv:2609.34949 — arXiv (en), https://arxiv.org/abs/2609.34949 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4166c255b20e (Metraipolis archive dc_4166c255b20e, sha256 d211297ad2fe45c25a297b37ebc46477a49daee29df4ee94fb27c3d4f1987ad4)
BibTeX
@misc{dc4166c255b20e,
title = {VD-DeepStack: Bridging Visual Comparison and Language Reasoning for Few-Shot Anomaly Detection — arXiv:2609.34949},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34949},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4166c255b20e; sha256 d211297ad2fe45c25a297b37ebc46477a49daee29df4ee94fb27c3d4f1987ad4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34949. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Few-shot visual anomaly detection is fundamentally a visual comparison task, requiring fine-grained inspection of a query against normal references. Many recent methods based on large vision-language models (LVLMs) emphasize comparative reasoning through language chain-of-thought. Yet discrete, abstract descriptions may underrepresent dense, fine-grained visual differences, leaving a gap between visual comparison and its expression in language. To address this gap, we propose Visual Difference DeepStack (VD-DeepStack), which explicitly conditions language reasoning on query-reference visual differences. Specifically, we fuse DINO features with the LVLM visual hierarchy to strengthen fine-grained representations, then construct dense difference evidence from residuals between query features and softly matched reference features. The difference-evidence path injects spatially weighted difference vectors into query-image states at multiple decoder depths, while an auxiliary visual-context path provides fine-grained appearance information to support their interpretation. Experiments on 4 industrial and 2 medical anomaly benchmarks demonstrate substantial improvements in few-shot anomaly detection over baselines relying on textual comparative reasoning. These results support mitigating the visual comparison-reasoning gap through the joint design of comparison representations and their integration into the decoder. Code will be released upon acceptance. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.34949 — 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 2026-10-07T20:29:01.726Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).