A Hierarchically Feature Reconstructed Autoencoder for Unsupervised Anomaly Detection

TL;DR

This paper introduces a simple, unsupervised anomaly detection method using a hierarchical feature autoencoder that leverages a pre-trained encoder and a decoder to effectively detect and localize anomalies without prior knowledge.

Contribution

It proposes a novel architecture that reconstructs hierarchical features for anomaly detection, improving accuracy and robustness over existing complex methods.

Findings

Outperforms state-of-the-art on multiple datasets

Does not require data augmentation or anomalous training data

Provides accurate anomaly localization

Abstract

Anomaly detection and localization without any manual annotations and prior knowledge is a challenging task under the setting of unsupervised learning. The existing works achieve excellent performance in the anomaly detection, but with complex networks or cumbersome pipelines. To address this issue, this paper explores a simple but effective architecture in the anomaly detection. It consists of a well pre-trained encoder to extract hierarchical feature representations and a decoder to reconstruct these intermediate features from the encoder. In particular, it does not require any data augmentations and anomalous images for training. The anomalies can be detected when the decoder fails to reconstruct features well, and then errors of hierarchical feature reconstruction are aggregated into an anomaly map to achieve anomaly localization. The difference comparison between those features of encoder and decode lead to more accurate and robust localization results than the comparison in single feature or pixel-by-pixel comparison in the conventional works. Experiment results show that the proposed method outperforms the state-of-the-art methods on MNIST, Fashion-MNIST, CIFAR-10, and MVTec Anomaly Detection datasets on both anomaly detection and localization.