SLSG: Industrial Image Anomaly Detection by Learning Better Feature Embeddings and One-Class Classification
This addresses the challenge of detecting logical anomalies in industrial images, which is important for quality control, but the approach appears incremental as it builds on existing methods with specific enhancements.
The paper tackled the problem of industrial image anomaly detection under one-class classification by proposing SLSG, a network that uses self-supervised learning and self-attentive graph convolution to improve feature embeddings and one-class classification, achieving superior performance on benchmark datasets.
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.