Metraipolis › archive › dc_3d2efc016f5d
Agentic Ensemble with Vision-Language Models for Visual Anomaly Detection — arXiv:2610.28560
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.28560
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-21T07:07:10.080Z
- SHA-256 of the archived text
9b95ad09015009a8a53432b4687d0b7e3e1e0030372ebab6068ac78d331caf15- Stable URL of this page
https://metraipolis.com/documento/dc_3d2efc016f5d
How to cite
Agentic Ensemble with Vision-Language Models for Visual Anomaly Detection — arXiv:2610.28560 — arXiv (en), https://arxiv.org/abs/2610.28560 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3d2efc016f5d (Metraipolis archive dc_3d2efc016f5d, sha256 9b95ad09015009a8a53432b4687d0b7e3e1e0030372ebab6068ac78d331caf15)
BibTeX
@misc{dc3d2efc016f5d,
title = {Agentic Ensemble with Vision-Language Models for Visual Anomaly Detection — arXiv:2610.28560},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.28560},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3d2efc016f5d; sha256 9b95ad09015009a8a53432b4687d0b7e3e1e0030372ebab6068ac78d331caf15},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.28560. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Visual anomaly detection aims to detect abnormal objects, while anomaly samples are often scarce during model training. Assembling multiple pretrained detectors can help by leveraging their transferable image scores and anomaly maps. However, most existing ensemble methods apply fixed fusion rules over saved predictions which struggle when pretrained detectors clearly disagree due to different training objectives, priors, and visual representations. To this end, we design AnomalyAgent, a post-training fusion framework for accurate visual anomaly detection. AnomalyAgent aligns heterogeneous scores and maps, summarizes score- and region-level disagreement, and treats fusion as a finite action-selection problem. It implements two types of actions: 1) score actions that determine how to fuse image-level detector confidence via consensus, robust aggregation, detector weighting, or score-map consistency; 2) map actions that fuse dense anomaly responses via consensus, detector weighting, geometric aggregation, or disagreement correction. A constrained vision-language model (VLM) is introduced to inspect high-conflict samples and select valid score action and map action to produce the final prediction. We evaluate AnomalyAgent on MVTec AD and VisA as primary benchmarks, together with seven additional public anomaly benchmarks and Real-IAD for large-scale score-level evaluation. Across these benchmarks, AnomalyAgent consistently improves over equal-weight fusion and achieves the best mean image AUROC and pixel AP among the compared fusion methods on MVTec AD and VisA, while demonstrating robust transfer across additional anomaly domains. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.28560 — 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 2026-10-21T07:05:43.488Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).