Although industrial anomaly detection (AD) technology has made significant progress in recent years, generating realistic anomalies and learning priors knowledge of normal remain challenging tasks. In this study, we propose an end-to-end industrial anomaly segmentation method called FractalAD. Training samples are obtained by synthesizing fractal images and patches from normal samples. This fractal anomaly generation method is designed to sample the full morphology of anomalies. Moreover, we designed a backbone knowledge distillation structure to extract prior knowledge contained in normal samples. The differences between a teacher and a student model are converted into anomaly attention using a cosine similarity attention module. The proposed method enables an end-to-end semantic segmentation network to be used for anomaly detection without adding any trainable parameters to the backbone and segmentation head. The results of ablation studies confirmed the effectiveness of fractal anomaly generation and backbone knowledge distillation. The results of performance experiments showed that FractalAD achieved competitive results on the MVTec AD dataset compared with other state-of-the-art anomaly detection methods.

翻译：尽管工业异常检测技术近年来取得了显著进展，但生成逼真的异常样本并学习正常样本的先验知识仍是具有挑战性的任务。本研究提出了一种名为FractalAD的端到端工业异常分割方法。训练样本通过将分形图像与正常样本的补丁进行合成获得。这种分形异常生成方法旨在对异常的全形态进行采样。此外，我们设计了一种骨干知识蒸馏结构，用于提取正常样本中包含的先验知识。通过余弦相似度注意力模块，将教师模型与学生模型之间的差异转换为异常注意力。所提出的方法使得端到端语义分割网络无需向骨干网络及分割头添加任何可训练参数即可用于异常检测。消融实验结果证实了分形异常生成与骨干知识蒸馏的有效性。性能实验结果表明，与当前其他最先进的异常检测方法相比，FractalAD在MVTec AD数据集上取得了具有竞争力的结果。