Novelty Detection via Robust Variational Autoencoding
arXiv:2006.05534
Abstract
We propose a new method for novelty detection that can tolerate high corruption of the training points, whereas previous works assumed either no or very low corruption. Our method trains a robust variational autoencoder (VAE), which aims to generate a model for the uncorrupted training points. To gain robustness to high corruption, we incorporate the following four changes to the common VAE: 1. Extracting crucial features of the latent code by a carefully designed dimension reduction component for distributions; 2. Modeling the latent distribution as a mixture of Gaussian low-rank inliers and full-rank outliers, where the testing only uses the inlier model; 3. Applying the Wasserstein-1 metric for regularization, instead of the Kullback-Leibler (KL) divergence; and 4. Using a robust error for reconstruction. We establish both robustness to outliers and suitability to low-rank modeling of the Wasserstein metric as opposed to the KL divergence. We illustrate state-of-the-art results on standard benchmarks.
References in corpus (19)
- Auto-Encoding Variational Bayes
- Can AI help in screening Viral and COVID-19 pneumonia?
- Deep Learning for Anomaly Detection: A Survey
- A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
- Statistical Aspects of Wasserstein Distances
- Deep Anomaly Detection Using Geometric Transformations
- Adversarial Autoencoders
- Median K-flats for hybrid linear modeling with many outliers
- Generative Probabilistic Novelty Detection with Adversarial Autoencoders
- An Overview of Robust Subspace Recovery
- A Novel M-Estimator for Robust PCA
- Fast, Robust and Non-convex Subspace Recovery
- Clustering and Unsupervised Anomaly Detection with L2 Normalized Deep Auto-Encoder Representations
- VELC: A New Variational AutoEncoder Based Model for Time Series Anomaly Detection
- A Well-Tempered Landscape for Non-convex Robust Subspace Recovery
- lp-Recovery of the Most Significant Subspace among Multiple Subspaces with Outliers
- Robust Variational Autoencoder
- Robust Subspace Recovery with Adversarial Outliers
- Deep Variational Semi-Supervised Novelty Detection