Anomaly detection is crucial to the advanced identification of product defects such as incorrect parts, misaligned components, and damages in industrial manufacturing. Due to the rare observations and unknown types of defects, anomaly detection is considered to be challenging in machine learning. To overcome this difficulty, recent approaches utilize the common visual representations from natural image datasets and distill the relevant features. However, existing approaches still have the discrepancy between the pre-trained feature and the target data, or require the input augmentation which should be carefully designed particularly for the industrial dataset. In this paper, we introduce ReConPatch, which constructs discriminative features for anomaly detection by training a linear modulation attached to a pre-trained model. ReConPatch employs contrastive representation learning to collect and distribute features in a way that produces a target-oriented and easily separable representation. To address the absence of labeled pairs for the contrastive learning, we utilize two similarity measures, pairwise and contextual similarities, between data representations as a pseudo-label. Unlike previous work, ReConPatch achieves robust anomaly detection performance without extensive input augmentation. Our method achieves the state-of-the-art anomaly detection performance (99.72%) for the widely used and challenging MVTec AD dataset.

翻译：异常检测对于工业制造中产品缺陷（如错误零件、部件错位及损伤）的早期识别至关重要。由于缺陷样本稀少且类型未知，异常检测被视为机器学习中的一项挑战。为克服这一困难，近期研究方法利用自然图像数据集的通用视觉表示，并提取相关特征。然而，现有方法仍存在预训练特征与目标数据之间的差异，或需要针对工业数据集精心设计输入增强。本文提出ReConPatch方法，通过训练附加于预训练模型的线性调制模块，构建用于异常检测的判别性特征。ReConPatch采用对比表示学习，以生成面向目标且易于分离的表示方式收集和分布特征。为解决对比学习中缺乏标注样本对的问题，我们利用数据表示之间的两类相似度——成对相似度与上下文相似度——作为伪标签。与先前工作不同，ReConPatch无需大量输入增强即可实现稳健的异常检测性能。所提方法在广泛应用且具有挑战性的MVTec AD数据集上取得了当前最优的异常检测性能（99.72%）。