Image anomaly detection (IAD) is an urgent issue that needs to be addressed in modern industrial manufacturing (IM). Recently, many advanced algorithms have been released, but their performance varies greatly due to non-uniformed settings. That is, researchers find it difficult to analyze because they are designed for different or specific cases in IM. To eliminate this problem, we first propose a uniform IAD setting to systematically assess the effectiveness of these algorithms, mainly considering three aspects of supervision level (unsupervised, fully supervised), learning paradigm (few-shot, continual, noisy label), and efficiency (memory usage, inference speed). Then, we skillfully construct a comprehensive image anomaly detection benchmark (IM-IAD), which includes 19 algorithms on 7 major datasets with the same setting. Our extensive experiments (17,017 total) provide new insights into the redesign or selection of the IAD algorithm under uniform conditions. Importantly, the proposed IM-IAD presents feasible challenges and future directions for further work. We believe that this work can have a significant impact on the IAD field. To foster reproducibility and accessibility, the source code of IM-IAD is uploaded on the website, https://github.com/M-3LAB/IM-IAD.

翻译：图像异常检测（IAD）是现代工业制造（IM）中亟待解决的关键问题。近年来，尽管涌现出大量先进算法，但由于设置不统一，其性能差异显著——研究人员发现难以进行分析，原因在于这些算法往往针对IM中不同或特定场景设计。为消除这一难题，我们首先提出统一的IAD设置，系统评估该类算法的有效性，主要考量三个维度：监督层级（无监督、全监督）、学习范式（小样本、持续学习、噪声标签）以及效率（内存占用、推理速度）。随后，我们巧妙构建了综合性图像异常检测基准（IM-IAD），涵盖7个主要数据集上的19种算法，均采用相同设置。通过广泛实验（总计17,017次），我们为在统一条件下重新设计或选择IAD算法提供了全新见解。重要的是，所提出的IM-IAD为后续工作提出了可行挑战与未来方向。我们相信该工作将对IAD领域产生重要影响。为促进可复现性与可访问性，IM-IAD的源代码已上传至网站：https://github.com/M-3LAB/IM-IAD。