Metraipolis › archive › dc_ddaaf053a583
DPA: Decoupling Product-Agnostic Anomaly Representations for Zero-shot Anomaly Generation — arXiv:2609.02075
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02075
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T05:49:51.462Z
- SHA-256 of the archived text
1a2ac78d2449516c302ca7503324184b93359fb1295e21cf4226ec6c86b33e4f- Stable URL of this page
https://metraipolis.com/documento/dc_ddaaf053a583
How to cite
DPA: Decoupling Product-Agnostic Anomaly Representations for Zero-shot Anomaly Generation — arXiv:2609.02075 — arXiv (en), https://arxiv.org/abs/2609.02075 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ddaaf053a583 (Metraipolis archive dc_ddaaf053a583, sha256 1a2ac78d2449516c302ca7503324184b93359fb1295e21cf4226ec6c86b33e4f)
BibTeX
@misc{dcddaaf053a583,
title = {DPA: Decoupling Product-Agnostic Anomaly Representations for Zero-shot Anomaly Generation — arXiv:2609.02075},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02075},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ddaaf053a583; sha256 1a2ac78d2449516c302ca7503324184b93359fb1295e21cf4226ec6c86b33e4f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02075. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Industrial anomaly detection benefits from anomaly samples, yet newly deployed products typically provide only normal images, making anomaly samples difficult to collect. Zero-shot anomaly generation offers a promising solution which avoids collection of target-product anomalies. However, existing methods mainly rely on texture images or text descriptions as anomaly sources, which often produce unrealistic anomalies. Observing that similar anomalies can recur across different products, we propose anomaly transfer-based zero-shot generation, which reuses real anomalies from existing source products, making target-product anomalies no longer necessary to generate realistic anomalious samples for unseen target products. Since not every anomaly type suits the target product, an anomaly type filtering mechanism first selects plausible source types. To transfer selected anomaly, we propose DPA, a diffusion-based framework that decouples product-agnostic anomaly representations. Instead of directly extracting anomaly representations, DPA learns product-irrelevant anomaly embeddings through training with the mismatched data pair, enabling transferable anomaly concept learning across products. Furthermore, we design an adaptive mask-guided pipeline that leverages adaptive masks to control the positional and geometric plausibility of generated anomalies during generation. A training-free anomaly labeling module is further introduced to produce pixel-level annotations aligned with generated anomalies. Extensive experiments on MVTec-AD, VisA, and a dedicated anomaly-transfer benchmark demonstrate that the proposed setting and DPA generate more realistic anomalies and significantly improve downstream anomaly detection performance under both zero-shot and few-shot settings. Source code and models will be released. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.02075 — 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 2026-10-17T05:25:58.061Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).