Adaptive aggregation-distillation autoencoder for unsupervised anomaly detection
作者：
Highlights：
• We propose the adaptive aggregation-distillation autoencoder for unsupervised anomaly detection, which considers the diversity of normal patterns and provides a strong guarantee for anomaly detection during training sets containing anomalies.
• A density-based landmark is designed to represent diverse normal patterns, which can adaptively update the location and quantity of landmarks during training.
• An aggregation-distillation mechanism is built upon the landmark selection in respect to landmark-guided convex polygon reconstruction for minimizing the intra-class variation and differentiating normal from abnormal patterns.
• We achieve the state-of-the-art performance on standard benchmarks for unsupervised anomaly detection in ten real-world datasets from different application domains.
摘要
•We propose the adaptive aggregation-distillation autoencoder for unsupervised anomaly detection, which considers the diversity of normal patterns and provides a strong guarantee for anomaly detection during training sets containing anomalies.•A density-based landmark is designed to represent diverse normal patterns, which can adaptively update the location and quantity of landmarks during training.•An aggregation-distillation mechanism is built upon the landmark selection in respect to landmark-guided convex polygon reconstruction for minimizing the intra-class variation and differentiating normal from abnormal patterns.•We achieve the state-of-the-art performance on standard benchmarks for unsupervised anomaly detection in ten real-world datasets from different application domains.
论文关键词：Anomaly detection,Aggregation-distillation mechanism,Autoencoders,Unsupervised learning
论文评审过程：Received 21 February 2022, Revised 18 June 2022, Accepted 9 July 2022, Available online 11 July 2022, Version of Record 18 July 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2022.108897
