面向工业异常检测的定制化变换不变性
Tailored Transformation Invariance for Industrial Anomaly Detection
AI总结：
本文提出局部窗口方法 LWinNN，在 kNN 与复杂方法之间折中，仅保留有限平移不变性，从而在工业异常检测中显著提升准确率并降低训练与测试时间。
摘要：
工业异常检测（IAD）是计算机视觉异常检测中的一个子问题，由于其在现实场景中的适用性而受到越来越多的关注。近期研究关注如何提取最具信息量的特征，这与仅使用预训练特征的较早期 kNN 方法形成对比。然而，这些近期方法的训练成本要高得多，可能会使现实应用变得更加复杂。仔细研究与变换不变性相关的文献后，我们得出一个观点：流行的基准测试只需要对轻微平移具有鲁棒性。基于这一观点，我们提出了 LWinNN，一种基于局部窗口的方法，它在具有完全平移不变性或完全没有平移不变性的 kNN 方法之间建立了一个折中方案。我们的实验表明，这一微小改动显著提高了准确率，同时降低了训练和测试时间。这给我们带来两点启示：第一，通过有效利用有限的可用数据，kNN 方法与更复杂的当前最优方法之间的差距仍然可以缩小；第二，我们关于只需要有限平移不变性的假设凸显了未来工作可能关注的领域，以及对空间上更具多样性的基准测试的需求，希望我们的方法能够为此类基准测试提供新的基线。我们的代码可在 https://github.com/marietteschonfeld/LWinNN 找到。
英文摘要：
Industrial Anomaly Detection (IAD) is a subproblem within Computer Vision Anomaly Detection that has been receiving increasing amounts of attention due to its applicability to real-life scenarios. Recent research has focused on how to extract the most informative features, contrasting older kNN-based methods that use only pretrained features. These recent methods are much more expensive to train however and could complicate real-life application. Careful study of related work with regards to transformation invariance leads to the idea that popular benchmarks require robustness to only minor translations. With this idea we then formulate LWinNN, a local window based approach that creates a middle ground between kNN based methods that have either complete or no translation invariance. Our experiments demonstrate that this small change increases accuracy considerably, while simultaneously decreasing both train and test time. This teaches us two things: first, the gap between kNN-based approaches and more complex state-of-the-art methodology can still be narrowed by effective usage of the limited data available. Second, our assumption of requiring only limited translation invariance highlights potential areas of interest for future work and the need for more spatially diverse benchmarks, for which our method can hopefully serve as a new baseline. Our code can be found at https://github.com/marietteschonfeld/LWinNN .
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。
