A Novel Anomaly Detection Method for Strip Steel Based on Multi-Scale Knowledge Distillation and Feature Information Banks Network

To address the problem of image imbalance in the surface inspection of strip steel, this study proposes a novel anomaly detection method based on multi-scale knowledge distillation (Ms-KD) and a block domain core information module (BDCI) to quickly screen abnormal images. This method utilizes the multi-scale knowledge distillation technique to enable the student network to learn the ability to extract normal image information under the source network pre-trained on ImageNet. At the same time, the optimal storage of block-level features is used to extract low-level and high-level information from intermediate layers and establish a feature bank, which is searched for core subset libraries using a greedy nearest neighbor selection mechanism. By using the Ms-KD module, the student model can understand the abnormal data more comprehensively so as to better capture the information in the data to solve the imbalance of abnormal data. To verify the validity of the proposed method, a completely new dataset called strip steel anomaly detection for few-shot learning (SSAD-FSL) was constructed, which involved image-level and pixel-level annotations of surface defects on cold-rolled and hot-rolled strip steel. By comparing with other state-of-the-art methods, the proposed method performs well on image-level area under the receiver operating characteristic curve (AUROC), reaching a high level of 0.9868, and for pixel-level per region overlap (PRO) indicators, the method also achieves the best score of 0.9896. Through a large number of experiments, the effectiveness of our proposed method in strip steel defect anomaly detection is fully proven.

Automated summary

This study proposes a novel anomaly detection method based on multi-scale knowledge distillation (Ms-KD) and a block domain core information module (BDCI) to quickly screen abnormal images in the surface inspection of strip steel. By utilizing the multi-scale knowledge distillation technique and the optimal storage of block-level features, the proposed method enables the student network to learn normal image information and better capture abnormal data to solve the imbalance problem. Experimental results showed the effectiveness of this method in strip steel defect anomaly detection, achieving high performance in image-level AUROC and pixel-level PRO indicators compared to state-of-the-art methods.