基于模式生成与对比网络的无监督工业异常检测
Unsupervised Industrial Anomaly Detection via Pattern Generative and Contrastive Networks
AI总结：
针对工业异常检测中缺陷样本不足、传统方法对纹理变化鲁棒性差的问题，提出基于ViT的模式生成-对比无监督检测网络，结合分层学习与双向推理，在MVTec数据集上达99.8% AUC，性能超现有最优方法。
摘要：
在工业生产中，难以收集足够的缺陷图像来训练深度学习网络。因此，现有的工业异常检测方法倾向于使用基于CNN（卷积神经网络）的无监督检测与定位网络来完成该任务。然而，由于传统端到端网络在高维空间中拟合非线性模型存在障碍，当新信号出现变化时，这些方法往往会失效。此外，这类方法本质上是通过对正常图像的特征进行聚类来构建记忆库，导致其对纹理变化的鲁棒性不足。针对这一问题，我们提出了基于Vision Transformer（ViT，视觉Transformer）的无监督异常检测网络，该网络利用分层任务学习和人类经验来提升可解释性。我们的网络由模式生成网络和对比网络组成：模式生成网络使用两个基于ViT的编码器模块提取连续两个图像块的特征，再通过基于ViT的解码器模块学习这些特征的人工设计风格并预测第三个图像块；之后，我们使用基于Siamese（孪生）的网络计算生成图像块与原始图像块的相似度；最后，通过双向推理策略优化异常定位结果。在公开数据集MVTec数据集上的对比实验表明，我们的方法达到了99.8%的AUC（曲线下面积），超越了此前的最优方法。此外，我们在自制的皮革和布料数据集上进行了定性验证，精准的分割结果有力证明了该方法在异常检测中的准确性。
英文摘要：
It is hard to collect enough flaw images for training deep learning network in industrial production. Therefore, existing industrial anomaly detection methods prefer to use CNN-based unsupervised detection and localization network to achieve this task. However, these methods always fail when there are varieties happened in new signals since traditional end-to-end networks suffer barriers of fitting nonlinear model in high-dimensional space. Moreover, they have a memory library by clustering the feature of normal images essentially, which cause it is not robust to texture change. To this end, we propose the Vision Transformer based (VIT-based) unsupervised anomaly detection network. It utilizes a hierarchical task learning and human experience to enhance its interpretability. Our network consists of pattern generation and comparison networks. Pattern generation network uses two VIT-based encoder modules to extract the feature of two consecutive image patches, then uses VIT-based decoder module to learn the human designed style of these features and predict the third image patch. After this, we use the Siamese-based network to compute the similarity of the generation image patch and original image patch. Finally, we refine the anomaly localization by the bi-directional inference strategy. Comparison experiments on public dataset MVTec dataset show our method achieves 99.8% AUC, which surpasses previous state-of-the-art methods. In addition, we give a qualitative illustration on our own leather and cloth datasets. The accurate segment results strongly prove the accuracy of our method in anomaly detection.
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。
