Adversarially Learned Anomaly Detection

By Houssam Zenati, Manon Romain, Chuan-Sheng Foo, Bruno Lecouat, Vijay Ramaseshan Chandrasekhar. Industrial Conference on Data Mining, 2018

460 citations recorded by the source corpus.

Anomaly detection is a significant and hence well-studied problem. However, developing effective anomaly detection methods for complex and high-dimensional data remains a challenge. As Generative Adversarial Networks (GANs) are able to model the complex high-dimensional distributions of real-world data, they offer a promising approach to address this challenge. In this work, we propose an anomaly detection method, Adversarially Learned Anomaly Detection (ALAD) based on bi-directional GANs, that derives adversarially learned features for the anomaly detection task. ALAD then uses reconstruction errors based on these adversarially learned features to determine if a data sample is anomalous. ALAD builds on recent advances to ensure data-space and latent-space cycle-consistencies and stabilize GAN training, which results in significantly improved anomaly detection performance. ALAD achieves state-of-the-art performance on a range of image and tabular datasets while being several hundred-fold faster at test time than the only published GAN-based method.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/5f61089d3d548a515f01b473f0119137d1f340d4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

USAD: UnSupervised Anomaly Detection on Multivariate Time Series (2020, background): “The Adversarially Learned Anomaly Detection (ALAD) [19] is based on bi-directional GANs, that derives adversarially learned features for the anomaly detection task.”
OpenGAN: Open-Set Recognition via Open Data Generation (2021, unknown): “There are many other GAN-based open-set methods, such as training BiGANs [47, 55, 56] or Table 2: Our technical insights apply to other GAN-based openset discrimination methods: 1) using BiGAN-discriminator as the open likelihood function works better than using reconstruction errors (BiGAN d vs.”
Deep Anomaly Detection with Deviation Networks (2019, methodology): “Existing deep anomaly detection1 methods [2, 7, 19, 20, 22, 29, 30] address these two challenges by using unsupervised deep learning to model the normal class in a two-step approach (i.”
Student-Teacher Feature Pyramid Matching for Anomaly Detection (2021, background): “The main weakness of these approaches comes from the excellent generalization ability of the deep models, including variational autoencoder [3], robust autoencoder [47], conditional GAN [2], and bi-directional GAN [46], which probably allows anomalous images to be faithfully reconstructed.”
Deep Learning for Anomaly Detection (2020, methodology): “2 ALAD [171] Keras https://git.”
ADBench: Anomaly Detection Benchmark (2022, background): “For instance, some semi-supervised models are trained only on normal samples, and detect anomalies that deviate from the normal representations learned in the training process [7, 8, 188].”
Learning Neural Random Fields with Inclusive Auxiliary Generators (2018, background): “Adversarially Learned Anomaly Detection (ALAD) [59] uses a bi-directional GAN which needs one more network (the inference network) in addition to the generator and the discriminator networks.”
A Unifying Review of Deep and Shallow Anomaly Detection (2020, methodology): “The major approaches to deep AD include deep AE variants [44], [51], [54], [125]–[135], deep one-class classification [136]–[145], methods based on DGMs, such as GANs [50], [56], [146]–[151], and recent self-supervised methods [152]–[156].”