Feature Encoding with AutoEncoders for Weakly-supervised Anomaly Detection

TL;DR

This paper introduces a novel feature encoding strategy using autoencoders for weakly-supervised anomaly detection, transforming input data into meaningful representations to improve detection performance.

Contribution

It proposes a new autoencoder-based encoding method and a network architecture that effectively utilize these representations for anomaly detection.

Findings

Outperforms existing methods in anomaly detection accuracy

Utilizes three factors: hidden representation, residual vector, and reconstruction error

Demonstrates robustness with limited labeled anomaly data

Abstract

Weakly-supervised anomaly detection aims at learning an anomaly detector from a limited amount of labeled data and abundant unlabeled data. Recent works build deep neural networks for anomaly detection by discriminatively mapping the normal samples and abnormal samples to different regions in the feature space or fitting different distributions. However, due to the limited number of annotated anomaly samples, directly training networks with the discriminative loss may not be sufficient. To overcome this issue, this paper proposes a novel strategy to transform the input data into a more meaningful representation that could be used for anomaly detection. Specifically, we leverage an autoencoder to encode the input data and utilize three factors, hidden representation, reconstruction residual vector, and reconstruction error, as the new representation for the input data. This representation amounts to encode a test sample with its projection on the training data manifold, its direction to its projection and its distance to its projection. In addition to this encoding, we also propose a novel network architecture to seamlessly incorporate those three factors. From our extensive experiments, the benefits of the proposed strategy are clearly demonstrated by its superior performance over the competitive methods.