Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders

Abstract

Detecting out of distribution (OOD) samples is of paramount importance in all Machine Learning applications. Deep generative modeling has emerged as a dominant paradigm to model complex data distributions without labels. However, prior work has shown that generative models tend to assign higher likelihoods to OOD samples compared to the data distribution on which they were trained. First, we propose Adversarial Mirrored Autoencoder (AMA), a variant of Adversarial Autoencoder, which uses a mirrored Wasserstein loss in the discriminator to enforce better semantic-level reconstruction. We also propose a latent space regularization to learn a compact manifold for in-distribution samples. The use of AMA produces better feature representations that improve anomaly detection performance. Second, we put forward an alternative measure of anomaly score to replace the reconstruction-based metric which has been traditionally used in generative model-based anomaly detection methods. Our method outperforms the current state-of-the-art methods for anomaly detection on several OOD detection benchmarks.

arXiv commentUpdated the paper with more OOD detection baselines. Performed ablation analysis on various components of AMA

References in corpus (23)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• mixup: Beyond Empirical Risk Minimization
• Spectral Normalization for Generative Adversarial Networks
• Pixel Recurrent Neural Networks
• Improved Training of Wasserstein GANs
• Deep Learning for Anomaly Detection: A Survey
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Adversarial Feature Learning
• Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
• A geometric analysis of subspace clustering with outliers
• Deep Structured Energy Based Models for Anomaly Detection
• Variational Approaches for Auto-Encoding Generative Adversarial Networks
• WAIC, but Why? Generative Ensembles for Robust Anomaly Detection
• Input complexity and out-of-distribution detection with likelihood-based generative models
• OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations
• Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality
• Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions
• Unsupervised Learning of Anomaly Detection from Contaminated Image Data using Simultaneous Encoder Training
• A Less Biased Evaluation of Out-of-distribution Sample Detectors
• Interpretable, Multidimensional, Multimodal Anomaly Detection with Negative Sampling for Detection of Device Failure
• Credit Card Fraud Detection in e-Commerce: An Outlier Detection Approach
• Provable Self-Representation Based Outlier Detection in a Union of Subspaces
• Dual Principal Component Pursuit

Cited by in corpus (5)

• A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges
• SAFE-OCC: A Novelty Detection Framework for Convolutional Neural Network Sensors and its Application in Process Control
• Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators
• Anomaly Detection via Self-organizing Map
• CVAD: A generic medical anomaly detector based on Cascade VAE