Metraipolis › archive › dc_1745f7ac871e
RADIOlogy: A Single-Pass Approach to Training-Free Zero-Shot Anomaly Detection — arXiv:2610.40580
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40580
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:43:44.528Z
- SHA-256 of the archived text
edd10c58121c99c0e48226fdaa950097a4a9d1a0f6b647a9f0dd511161715ab8- Stable URL of this page
https://metraipolis.com/documento/dc_1745f7ac871e
How to cite
RADIOlogy: A Single-Pass Approach to Training-Free Zero-Shot Anomaly Detection — arXiv:2610.40580 — arXiv (en), https://arxiv.org/abs/2610.40580 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1745f7ac871e (Metraipolis archive dc_1745f7ac871e, sha256 edd10c58121c99c0e48226fdaa950097a4a9d1a0f6b647a9f0dd511161715ab8)
BibTeX
@misc{dc1745f7ac871e,
title = {RADIOlogy: A Single-Pass Approach to Training-Free Zero-Shot Anomaly Detection — arXiv:2610.40580},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40580},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1745f7ac871e; sha256 edd10c58121c99c0e48226fdaa950097a4a9d1a0f6b647a9f0dd511161715ab8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40580. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Current zero-shot anomaly detection methods often rely on complex prompt-learning techniques or computationally expensive sliding-window strategies to achieve fine-grained visual alignment to detect small-scale anomalies. This reliance stems from the fundamental limitation of standard CLIP architectures, where [CLS] token attention and spatial patch pooling struggle to capture subtle, localized anomaly features. While prompt-learning approaches aim to bridge this gap, they typically require a large number of ground-truth segmentation masks from auxiliary datasets, which are often unavailable in specialized domains. In this work, we show an emerging property of multi-head attention pooling in vision-language models: remarkable zero-shot anomaly localization and detection right out of the box. We translate this property into a single-pass anomaly detection technique, RADIOlogy, that does not require dense, windowed execution and significantly outperforms other training-free baselines. Instead, the method relies on a simple contrastive scoring approach that compares the average similarity between vision features and a suite of normal and abnormal prompts. Furthermore, we leverage the agglomerative features of RADIO models to enhance pixel-level anomaly segmentation using a dense anomaly refinement pipeline. Finally, we show how the vision-language family of training-free zero-shot anomaly detection techniques can be applied successfully to the medical domain with minimal modifications. Code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.40580 — 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 2026-11-01T02:16:43.993Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).