Anomaly Detection Based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillation

Ramirez Rivera, Adin; Khan, Adil; Bekkouch, Imad Eddine Ibrahim; Sheikh, Taimoor Shakeel

Abstract

Anomaly detection suffers from unbalanced data since anomalies are quite rare. Synthetically generated anomalies are a solution to such ill or not fully defined data. However, synthesis requires an expressive representation to guarantee the quality of the generated data. In this article, we propose a two-level hierarchical latent space representation that distills inliers' feature descriptors [through autoencoders (AEs)] into more robust representations based on a variational family of distributions (through a variational AE) for zero-shot anomaly generation. From the learned latent distributions, we select those that lie on the outskirts of the training data as synthetic-outlier generators. Also, we synthesize from them, i.e., generate negative samples without seen them before, to train binary classifiers. We found that the use of the proposed hierarchical structure for feature distillation and fusion creates robust and general representations that allow us to synthesize pseudo outlier samples. Also, in turn, train robust binary classifiers for true outlier detection (without the need for actual outliers during training). We demonstrate the performance of our proposal on several benchmarks for anomaly detection.

Citation

Ramirez Rivera, A., Khan, A., Bekkouch, I. E. I., & Sheikh, T. S. (2022). Anomaly Detection Based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillation. IEEE Transactions on Neural Networks and Learning Systems, 33(1), 281-291. https://doi.org/10.1109/TNNLS.2020.3027667

• Journal Article Type: Article
• Acceptance Date: Sep 24, 2020
• Online Publication Date: Oct 16, 2020
• Publication Date: Jan 1, 2022
• Deposit Date: Aug 28, 2024
• Publicly Available Date: Sep 13, 2024
• Journal: IEEE Transactions on Neural Networks and Learning Systems
• Print ISSN: 2162-237X
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Peer Reviewed: Peer Reviewed
• Volume: 33
• Issue: 1
• Pages: 281-291
• DOI: https://doi.org/10.1109/TNNLS.2020.3027667
• Keywords: Feature extraction; Unsupervised learning
• Public URL: https://hull-repository.worktribe.com/output/4792237