SLSG：通过学习更优特征嵌入与单类分类实现工业图像异常检测
SLSG: Industrial Image Anomaly Detection by Learning Better Feature Embeddings and One-Class Classification
AI总结：
针对工业图像异常检测中特征嵌入可区分性不足、单类分类正常特征描述不紧凑及逻辑异常检测效果差的问题，提出基于自监督学习与自注意力图卷积的SLSG网络，通过生成预训练、模拟异常对比及通用图结构建模提升检测性能，经基准实验验证效果优异。
摘要：
单类分类设定下的工业图像异常检测具备重要实用价值。然而，现有多数模型在进行特征嵌入时难以提取可区分的特征表示，在执行单类分类时难以构建正常特征的紧凑描述。这一问题的直接后果是，多数模型在检测违反上下文关系的逻辑异常时表现不佳。针对更高效、更全面的异常检测需求，我们提出一种基于自监督学习与自注意力图卷积的网络（SLSG）用于异常检测。SLSG利用生成式预训练网络辅助编码器学习正常模式的嵌入与位置关系推理。随后，SLSG通过模拟异常样本引入异常的伪先验知识。通过对比模拟异常，SLSG能够更好地归纳正常特征，并收窄用于单类分类的超球面。此外，通过构建更通用的图结构，SLSG对图像中元素间的稠密与稀疏关系进行全面建模，进一步强化了对逻辑异常的检测能力。在基准数据集上开展的大量实验表明，SLSG取得了优异的异常检测性能，验证了我们所提方法的有效性。
英文摘要：
Industrial image anomaly detection under the setting of one-class classification has significant practical value. However, most existing models struggle to extract separable feature representations when performing feature embedding and struggle to build compact descriptions of normal features when performing one-class classification. One direct consequence of this is that most models perform poorly in detecting logical anomalies which violate contextual relationships. Focusing on more effective and comprehensive anomaly detection, we propose a network based on self-supervised learning and self-attentive graph convolution (SLSG) for anomaly detection. SLSG uses a generative pre-training network to assist the encoder in learning the embedding of normal patterns and the reasoning of position relationships. Subsequently, SLSG introduces the pseudo-prior knowledge of anomaly through simulated abnormal samples. By comparing the simulated anomalies, SLSG can better summarize the normal features and narrow down the hypersphere used for one-class classification. In addition, with the construction of a more general graph structure, SLSG comprehensively models the dense and sparse relationships among elements in the image, which further strengthens the detection of logical anomalies. Extensive experiments on benchmark datasets show that SLSG achieves superior anomaly detection performance, demonstrating the effectiveness of our method.
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。
