Semi Supervised Anomaly Detection

Semi-supervised Anomaly Detection is a technique for identifying anomalous samples with limited labeled data, aiming to improve the accuracy and efficiency of anomaly detection by combining a small amount of labeled data with a large amount of unlabeled data. This method can effectively recognize abnormal patterns in images and videos in the field of computer vision, and has a wide range of application values, such as detecting abnormal behaviors in surveillance systems and defect detection in industrial production.