IM-IAD：制造业中的工业图像异常检测基准
IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing
AI总结：
针对工业制造场景下图像异常检测算法性能差异大、缺乏统一基准的问题，提出涵盖多监督级别、多学习范式与效率评估的IM-IAD基准，开展17017组实验提供算法选型参考并指明研究方向，代码已开源。
摘要：
图像异常检测（IAD）是工业制造（IM）领域一项新兴且重要的计算机视觉任务。近年来，许多先进算法被相继提出，但它们的性能在不同的工业制造场景下差异显著。我们意识到，缺乏统一的工业制造基准正在阻碍IAD方法在实际应用中的开发与落地，此外，研究人员也难以在没有统一基准的情况下对IAD算法进行分析。为解决这一问题，我们首次提出了一个统一的工业制造基准，用于评估各类算法的性能，该基准涵盖不同监督级别（无监督与全监督）、学习范式（少样本、持续学习与噪声标签）以及效率指标（内存占用与推理速度）。随后，我们构建了一个综合性的图像异常检测基准IM-IAD，包含7个主流数据集上的19种算法，且所有设置均保持统一。在IM-IAD上开展的共计17017组大量实验，为IAD算法的重新设计或选型提供了深入的洞见。此外，所提出的IM-IAD基准对现有算法提出了挑战，并指明了未来的研究方向。为提升可复现性与可获取性，IM-IAD的源代码已上传至网站https://github.com/M-3LAB/IM-IAD。
英文摘要：
Image anomaly detection (IAD) is an emerging and vital computer vision task in industrial manufacturing (IM). Recently, many advanced algorithms have been reported, but their performance deviates considerably with various IM settings. We realize that the lack of a uniform IM benchmark is hindering the development and usage of IAD methods in real-world applications. In addition, it is difficult for researchers to analyze IAD algorithms without a uniform benchmark. To solve this problem, we propose a uniform IM benchmark, for the first time, to assess how well these algorithms perform, which includes various levels of supervision (unsupervised versus fully supervised), learning paradigms (few-shot, continual and noisy label), and efficiency (memory usage and inference speed). Then, we construct a comprehensive image anomaly detection benchmark (IM-IAD), which includes 19 algorithms on seven major datasets with a uniform setting. Extensive experiments (17,017 total) on IM-IAD provide in-depth insights into IAD algorithm redesign or selection. Moreover, the proposed IM-IAD benchmark challenges existing algorithms and suggests future research directions. To foster reproducibility and accessibility, the source code of IM-IAD is uploaded on the website, https://github.com/M-3LAB/IM-IAD.
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。
