Latent-Insensitive autoencoders for Anomaly Detection

TL;DR

This paper introduces Latent-Insensitive autoencoders (LIS-AE), which leverage unlabeled similar domain data as negative examples to improve anomaly detection by shaping the latent space of autoencoders, with theoretical and empirical validation.

Contribution

The paper proposes a novel autoencoder training method using negative examples from similar domains to enhance anomaly detection, supported by theoretical analysis and extensive experiments.

Findings

Significant performance improvements in anomaly detection tasks

Effective use of unlabeled similar domain data as negative examples

Theoretical justification for the training process

Abstract

Reconstruction-based approaches to anomaly detection tend to fall short when applied to complex datasets with target classes that possess high inter-class variance. Similar to the idea of self-taught learning used in transfer learning, many domains are rich with similar unlabelled datasets that could be leveraged as a proxy for out-of-distribution samples. In this paper we introduce Latent-Insensitive autoencoder (LIS-AE) where unlabeled data from a similar domain is utilized as negative examples to shape the latent layer (bottleneck) of a regular autoencoder such that it is only capable of reconstructing one task. We provide theoretical justification for the proposed training process and loss functions along with an extensive ablation study highlighting important aspects of our model. We test our model in multiple anomaly detection settings presenting quantitative and qualitative analysis showcasing the significant performance improvement of our model for anomaly detection tasks.