Flow-based SVDD for anomaly detection
This work addresses a specific technical challenge in anomaly detection for applications requiring robust outlier identification, though it is incremental as it builds on existing SVDD principles with a new model instantiation.
The authors tackled the problem of hypersphere collapse in deep Support Vector Data Description (SVDD) for anomaly detection by proposing FlowSVDD, a flow-based one-class classifier that prevents this issue and achieves comparable results to state-of-the-art methods while significantly outperforming related deep SVDD approaches on benchmark datasets.
We propose FlowSVDD -- a flow-based one-class classifier for anomaly/outliers detection that realizes a well-known SVDD principle using deep learning tools. Contrary to other approaches to deep SVDD, the proposed model is instantiated using flow-based models, which naturally prevents from collapsing of bounding hypersphere into a single point. Experiments show that FlowSVDD achieves comparable results to the current state-of-the-art methods and significantly outperforms related deep SVDD methods on benchmark datasets.