Metraipolis › archive › dc_569a0403c299

CORE: Contrast-and-Reflect for Self-Supervised Prompt Optimization in Anomaly Synthesis — arXiv:2610.19610

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19610
License (as archived)
CC0-1.0
Archived
2026-10-15T21:56:14.798Z
SHA-256 of the archived text
4bbae6dc46b6b987d70b0b08e845507504b85b7e1a6362ef4f6f96e2e962fad6
Stable URL of this page
https://metraipolis.com/documento/dc_569a0403c299

How to cite

CORE: Contrast-and-Reflect for Self-Supervised Prompt Optimization in Anomaly Synthesis — arXiv:2610.19610 — arXiv (en), https://arxiv.org/abs/2610.19610 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_569a0403c299 (Metraipolis archive dc_569a0403c299, sha256 4bbae6dc46b6b987d70b0b08e845507504b85b7e1a6362ef4f6f96e2e962fad6)
BibTeX
@misc{dc569a0403c299,
  title = {CORE: Contrast-and-Reflect for Self-Supervised Prompt Optimization in Anomaly Synthesis — arXiv:2610.19610},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19610},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_569a0403c299; sha256 4bbae6dc46b6b987d70b0b08e845507504b85b7e1a6362ef4f6f96e2e962fad6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19610. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Industrial anomaly detection (AD) is bottlenecked by the scarcity of anomalous samples, making high-fidelity anomaly synthesis crucial for improving downstream performance. However, existing methods either rely on scarce real anomaly references or auxiliary data, while lacking complex reasoning and iterative optimization capabilities for generating realistic defects in open-set scenarios. To address these challenges, we propose CORE, a cost-efficient and training-free prompt optimization framework based on Large Multimodal Models (LMMs), which unifies zero-shot and one-shot anomaly synthesis. CORE first introduces an Anomaly Context Grounding module to transform sparse user context into defect-aware generation context, which is subsequently instantiated as structured anomaly prompts that disentangle normal-region preservation from anomaly-specific variation, enabling controllable and faithful defect generation. Furthermore, CORE autonomously refines prompts through a self-supervised contrast-and-reflect mechanism. This design empowers general-purpose LMMs to synthesize realistic anomalies under both zero-shot and one-shot settings without task-specific training. Extensive experiments on MVTec-AD and VisA demonstrate that CORE synthesizes realistic and diverse anomalies, yielding superior improvements in downstream AD performance. Furthermore, its model-agnostic and plug-and-play paradigm enables effortless integration with diverse LMMs, facilitating adaptation to unseen open-set scenarios.

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/2610.19610 — 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 2026-10-15T21:38:29.477Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).