<p>With the rapid development of deep learning technology, industrial anomaly detection technology has significantly improved its ability to handle large-scale images and point clouds. It has gradually been applied to complex industrial environments. However, current reviews of anomaly detection technology are often technology-oriented, and there is still a need for a systematic classification for practical industrial scenarios. Given these considerations, we will summarize and categorize the latest anomaly detection technologies from the perspective of specific industrial application scenarios, including 2D image anomaly detection, 3D object anomaly detection, and datasets. This application-oriented classification method can more effectively meet the practical needs of anomaly detection tasks in industrial production. Furthermore, we contribute to anomaly detection technology by delivering a comprehensive analysis of the current state and challenges in industrial anomaly detection, offering insights into the customization of deep learning for real-world industrial applications, and presenting an outlook for future research directions.</p>