Abstract
Image anomaly detection (IAD) is an emerging and vital computer vision task in industrial manufacturing (IM). Recently many advanced algorithms have been published, but their performance deviates greatly. We realize that the lack of actual IM settings most probably hinders the development and usage of these methods in real-world applications. As far as we know, IAD methods are not evaluated systematically. As a result, this makes it difficult for researchers to analyze them because they are designed for different or special cases. To solve this problem, we first propose a uniform IM setting to assess how well these algorithms perform, which includes several aspects, i.e., various levels of supervision (unsupervised vs. semi-supervised), few-shot learning, continual learning, noisy labels, memory usage, and inference speed. Moreover, we skillfully build a comprehensive image anomaly detection benchmark (IM-IAD) that includes 16 algorithms on 7 mainstream datasets with uniform settings. Our extensive experiments (17,017 in total) provide in-depth insights for IAD algorithm redesign or selection under the IM setting. Next, the proposed benchmark IM-IAD gives challenges as well as directions for the future. To foster reproducibility and accessibility, the source code of IM-IAD is uploaded on the website, this https URL.
Abstract (translated)
图像异常检测(IAD)是工业制造领域新兴且重要的计算机视觉任务。近年来,许多先进的算法都被发布,但它们的性能差异很大。我们意识到,缺乏实际IM设置很可能阻碍这些方法在现实世界中的应用和发展。据我们所知,IAD方法没有系统地评估。因此,这使得研究人员难以分析它们,因为它们是为不同或特殊情况设计的。为了解决这一问题,我们首先提出了一种统一的IM设置,以评估这些算法的性能,该设置包括多个方面,例如不同程度的监督(无监督和半监督)、少数次学习、持续学习、噪声标签、内存使用和推理速度。此外,我们巧妙地构建了一个 comprehensive image异常检测基准(IM-IAD),该基准包括在7个主流数据集上使用统一设置下的16个算法。我们的广泛实验(总共17,017次)为IM-IAD算法重新设计或选择提供了深入 insights。接下来,该提出的基准IM-IAD带来了挑战和未来的指南。为了促进可重复性和访问性,IM-IAD的源代码上传到网站上,这是httpsURL。
URL
https://arxiv.org/abs/2301.13359
