arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2501.15211cs.CV

他山之石,可以攻玉:基于跨域异常注入的零样本异常图像合成

"Stones from Other Hills can Polish Jade": Zero-shot Anomaly Image Synthesis via Cross-domain Anomaly Injection

National University of Defense Technology(国防科技大学);Academy of Military Science(军事科学院);North University of China(中北大学)

Siqi Wang, Yuanze Hu, Xinwang Liu, Siwei Wang, Guangpu Wang, Chuanfu Xu, Jie Liu, Ping Chen

AI总结:

本文提出跨域异常注入(CAI)方法,利用其他领域的真实异常实现无需训练的零样本异常合成,并构建领域无关异常数据集及CAI引导扩散机制,突破了异常数量限制,显著提升了工业图像异常检测性能。

摘要:

工业图像异常检测(IAD)是一个具有巨大价值的关键课题。由于异常的固有特性,特定现代工业领域中的真实异常(即领域特定异常)通常过于稀少而难以收集,这严重阻碍了IAD的发展。因此,零样本异常合成(ZSAS)作为一种关键技术应运而生,它能够在没有任何领域特定异常的情况下合成伪异常图像。然而,现有解决方案要么无法合成逼真的伪异常,要么需要繁琐的训练。为此,我们聚焦于ZSAS,并提出了一种全新的范式,能够同时实现逼真且无需训练的ZSAS。该范式基于一个长期被忽视的事实:尽管领域特定异常稀少,但来自其他领域的真实异常(即跨域异常)实际上是丰富的,并且可以直接应用于ZSAS。具体而言,我们的新ZSAS范式做出了三方面贡献:第一,我们提出了一种名为跨域异常注入(CAI)的新方法,该方法直接利用跨域异常,以无需训练的方式实现高度逼真的ZSAS。第二,为了给CAI提供充足的跨域异常,我们据我们所知构建了首个领域无关异常数据集,为ZSAS提供了丰富的真实异常模式。第三,我们提出了一种CAI引导的扩散机制,进一步突破了真实异常的数量限制,实现了无限的异常合成。我们与现有ZSAS解决方案的正面比较验证了我们的范式在IAD上的优越性能,并证明它是一种有效且实用的ZSAS解决方案。

英文摘要:

Industrial image anomaly detection (IAD) is a pivotal topic with huge value. Due to anomaly's nature, real anomalies in a specific modern industrial domain (i.e. domain-specific anomalies) are usually too rare to collect, which severely hinders IAD. Thus, zero-shot anomaly synthesis (ZSAS), which synthesizes pseudo anomaly images without any domain-specific anomaly, emerges as a vital technique for IAD. However, existing solutions are either unable to synthesize authentic pseudo anomalies, or require cumbersome training. Thus, we focus on ZSAS and propose a brand-new paradigm that can realize both authentic and training-free ZSAS. It is based on a chronically-ignored fact: Although domain-specific anomalies are rare, real anomalies from other domains (i.e. cross-domain anomalies) are actually abundant and directly applicable to ZSAS. Specifically, our new ZSAS paradigm makes three-fold contributions: First, we propose a novel method named Cross-domain Anomaly Injection (CAI), which directly exploits cross-domain anomalies to enable highly authentic ZSAS in a training-free manner. Second, to supply CAI with sufficient cross-domain anomalies, we build the first Domain-agnostic Anomaly Dataset within our best knowledge, which provides ZSAS with abundant real anomaly patterns. Third, we propose a CAI-guided Diffusion Mechanism, which further breaks the quantity limit of real anomalies and enable unlimited anomaly synthesis. Our head-to-head comparison with existing ZSAS solutions justifies our paradigm's superior performance for IAD and demonstrates it as an effective and pragmatic ZSAS solution.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑