Backpropagated Gradient Representations for Anomaly Detection

TL;DR

This paper introduces a novel anomaly detection method that leverages backpropagated gradients as data representations, achieving state-of-the-art results with high computational efficiency and simplicity.

Contribution

It proposes using backpropagated gradients for anomaly detection, a novel approach that outperforms existing methods in accuracy and efficiency.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Requires significantly fewer model parameters than competing methods.

Offers a computationally efficient and simple alternative to complex models.

Abstract

Learning representations that clearly distinguish between normal and abnormal data is key to the success of anomaly detection. Most of existing anomaly detection algorithms use activation representations from forward propagation while not exploiting gradients from backpropagation to characterize data. Gradients capture model updates required to represent data. Anomalies require more drastic model updates to fully represent them compared to normal data. Hence, we propose the utilization of backpropagated gradients as representations to characterize model behavior on anomalies and, consequently, detect such anomalies. We show that the proposed method using gradient-based representations achieves state-of-the-art anomaly detection performance in benchmark image recognition datasets. Also, we highlight the computational efficiency and the simplicity of the proposed method in comparison with other state-of-the-art methods relying on adversarial networks or autoregressive models, which require at least 27 times more model parameters than the proposed method.