This paper presents the first application of neural architecture search to the complex task of segmenting visual anomalies. Measurement of anomaly segmentation performance is challenging due to imbalanced anomaly pixels, varying region areas, and various types of anomalies. First, the region-weighted Average Precision (rwAP) metric is proposed as an alternative to existing metrics, which does not need to be limited to a specific maximum false positive rate. Second, the AutoPatch neural architecture search method is proposed, which enables efficient segmentation of visual anomalies without any training. By leveraging a pre-trained supernet, a black-box optimization algorithm can directly minimize computational complexity and maximize performance on a small validation set of anomalous examples. Finally, compelling results are presented on the widely studied MVTec dataset, demonstrating that AutoPatch outperforms the current state-of-the-art with lower computational complexity, using only one example per type of anomaly. The results highlight the potential of automated machine learning to optimize throughput in industrial quality control. The code for AutoPatch is available at: https://github.com/tommiekerssies/AutoPatch

翻译：本文首次将神经架构搜索应用于视觉异常分割这一复杂任务。由于异常像素分布不均、区域面积各异以及异常类型多样，异常分割性能的度量极具挑战性。首先，提出区域加权平均精度（rwAP）指标作为现有指标的替代方案，该指标无需限定于特定的最大假阳性率。其次，提出AutoPatch神经架构搜索方法，无需任何训练即可高效分割视觉异常。通过利用预训练的超网络，黑盒优化算法能够直接最小化计算复杂度，并在包含少量异常样本的验证集上最大化性能。最后，在广泛研究的MVTec数据集上展示了令人信服的结果，证明AutoPatch在仅使用每种异常类型一个样本的情况下，以更低的计算复杂度超越了当前最先进方法。这些结果凸显了自动化机器学习在优化工业质量控制吞吐量方面的潜力。AutoPatch的代码可在https://github.com/tommiekerssies/AutoPatch获取。