Unsupervised Anomaly Detection With Specified

Unsupervised anomaly detection refers to the technique of identifying data points that significantly deviate from normal patterns within an unlabelled dataset. When setting the anomaly ratio to 30%, this method aims to automatically discover 30% of the samples that are anomalies from the data, without predefining what is normal or abnormal. This technology holds significant application value in the field of computer vision, effectively improving the accuracy of anomaly event detection in images and videos, and enhancing the system's robustness and adaptability to unknown anomalies.