Adaptive aggregation-distillation autoencoder for unsupervised anomaly detection
- Resource Type
- ACADEMIC JOURNAL
- Authors
- Zhu, Jiaqi a; Deng, Fang ⁎, a; Zhao, Jiachen a; Chen, Jie a, b
- Source
- In Pattern Recognition November 2022 131
- Subject
- Language
- English
- ISSN
- 0031-3203
- E-ISSN
- DOI
- 10.1016/j.patcog.2022.108897
•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.