Clustering and Unsupervised Anomaly Detection with L2 Normalized Deep Auto-Encoder Representations

TL;DR

This paper demonstrates that applying an l2 normalization constraint to deep auto-encoder representations enhances clustering separability and improves unsupervised anomaly detection accuracy.

Contribution

It introduces a novel l2 normalization constraint during auto-encoder training that improves clustering and anomaly detection performance.

Findings

L2 normalization makes representations more separable and compact.

Clustering accuracy with k-means improves with normalized representations.

The proposed anomaly detection method outperforms previous deep methods.

Abstract

Clustering is essential to many tasks in pattern recognition and computer vision. With the advent of deep learning, there is an increasing interest in learning deep unsupervised representations for clustering analysis. Many works on this domain rely on variants of auto-encoders and use the encoder outputs as representations/features for clustering. In this paper, we show that an l2 normalization constraint on these representations during auto-encoder training, makes the representations more separable and compact in the Euclidean space after training. This greatly improves the clustering accuracy when k-means clustering is employed on the representations. We also propose a clustering based unsupervised anomaly detection method using l2 normalized deep auto-encoder representations. We show the effect of l2 normalization on anomaly detection accuracy. We further show that the proposed anomaly detection method greatly improves accuracy compared to previously proposed deep methods such as reconstruction error based anomaly detection.