从实验室到工厂：低质量工业图像上自监督/无监督缺陷检测的陷阱与指南
From Lab to Factory: Pitfalls and Guidelines for Self-/Unsupervised Defect Detection on Low-Quality Industrial Images
AI总结：
针对低质量工业图像上的无监督缺陷检测，本文指出常用方法在现实中的鲁棒性问题，评估两种先进模型，为从业者提供识别数据与模型问题的指南，并改进经验风险估计框架。
摘要：
工业大规模生产产品中与质量相关问题的检测和定位历来依赖人工检查，这既昂贵又容易出错。机器学习有潜力取代人工处理。因此，人们希望采用无监督（或自监督）方法，因为事先往往无法指定所有可能的缺陷。大量先前工作已证明常见的基于重建、嵌入和合成的方法在实验室环境中的适用性。然而，在实践中，我们观察到大多数方法不能很好地处理低数据质量，或在不利但典型的现实世界环境中表现出较低的鲁棒性。当这些方法表现不佳时，从业者可能很难识别实际的根本问题。更糟糕的是，经常报告的指标（如AUROC）在实践中很少适用，并可能给出误导性结果。在我们的设置中，我们尝试仅使用质量较低的RGB图像来识别喷丸锻造金属零件表面的细微异常，这是一种常见的工业场景。我们专门评估了两种最先进的模型，它们使我们能够在不获取新数据的情况下识别和改进生产数据中的质量问题。我们的贡献是为从业者提供指导，使他们能够在类似场景中可靠地识别与所选模型或数据相关的（缺乏）鲁棒性或不变性等问题。此外，我们举例说明了基于似然的方法中常见的陷阱和缺点，并概述了一个更适合现实世界场景的适当经验风险估计框架。
英文摘要：
The detection and localization of quality-related problems in industrially mass-produced products has historically relied on manual inspection, which is costly and error-prone. Machine learning has the potential to replace manual handling. As such, the desire is to facilitate an unsupervised (or self-supervised) approach, as it is often impossible to specify all conceivable defects ahead of time. A plethora of prior works have demonstrated the aptitude of common reconstruction-, embedding-, and synthesis-based methods in laboratory settings. However, in practice, we observe that most methods do not handle low data quality well or exude low robustness in unfavorable, but typical real-world settings. For practitioners it may be very difficult to identify the actual underlying problem when such methods underperform. Worse, often-reported metrics (e.g., AUROC) are rarely suitable in practice and may give misleading results. In our setting, we attempt to identify subtle anomalies on the surface of blasted forged metal parts, using rather low-quality RGB imagery only, which is a common industrial setting. We specifically evaluate two types of state-of-the-art models that allow us to identify and improve quality issues in production data, without having to obtain new data. Our contribution is to provide guardrails for practitioners that allow them to identify problems related to, e.g., (lack of) robustness or invariance, in either the chosen model or the data reliably in similar scenarios. Furthermore, we exemplify common pitfalls in and shortcomings of likelihood-based approaches and outline a framework for proper empirical risk estimation that is more suitable for real-world scenarios.
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。
