Anomaly Detection based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillation
This work addresses the challenge of rare anomalies in data for machine learning practitioners, offering an incremental improvement through a novel synthesis approach.
The paper tackles the problem of anomaly detection with unbalanced data by proposing a two-level hierarchical latent space representation for zero-shot anomaly synthesis, which enables training robust binary classifiers without needing actual outliers during training. The method demonstrates performance on several benchmarks, though specific numbers are not provided.
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 paper, we propose a two-level hierarchical latent space representation that distills inliers' feature-descriptors (through autoencoders) into more robust representations based on a variational family of distributions (through a variational autoencoder) 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. And, 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. And 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.