|M.Sc Student||Daniel Tal|
|Subject||Deep Variational Semi-Supervised Novelty Detection|
|Department||Department of Electrical Engineering||Supervisor||Dr. Aviv Tamar|
|Full Thesis text|
In anomaly detection (AD), or novelty detection (ND), one seeks to identify whether a test sample is abnormal, given a data set of normal samples. A recent and promising approach to AD relies on deep generative models, such as variational autoencoders (VAEs) and generative adversarial networks (GANs), for unsupervised learning of the normal data distribution. In semi-supervised anomaly detection (SSAD), the data also includes a small sample of labeled anomalies. In this work, we propose two variational methods for training VAEs for SSAD, which we term Max-Min Likelihood VAE (MML-VAE) and Dual Prior VAE (DP-VAE). The intuitive idea in both methods is to train the encoder to `separate' between latent vectors for normal and outlier data. We show that this idea can be derived from principled probabilistic formulations of the problem and propose simple and effective algorithms. Our methods can be applied to various data types, as we demonstrate on SSAD datasets ranging from natural images to astronomy and medicine, and can be combined with any VAE model architecture. When comparing to state-of-the-art SSAD methods that are not specific to particular data types, we obtain marked improvement in outlier detection. In addition, we show novelty detection applications in motion planning for robotics and sentiment analysis in natural language processing.