Clustering and Unsupervised Anomaly Detection with L2 Normalized Deep Auto-Encoder Representations
This work addresses the need for better unsupervised representation learning in clustering and anomaly detection, offering incremental improvements over existing auto-encoder-based methods.
The paper tackled the problem of improving clustering and unsupervised anomaly detection by applying an L2 normalization constraint during auto-encoder training, which made representations more separable and compact, leading to improved clustering accuracy and anomaly detection performance compared to existing deep methods.
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.