Clustering and Unsupervised Anomaly Detection with l<inf>2</inf> Normalized Deep Auto-Encoder Representations

Çağlar Aytekin, Xingyang Ni, Francesco Cricri, Emre Aksu

2018 · 108 citations · 12 references

Concepts

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 l <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> 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 l <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> normalized deep auto-encoder representations. We show the effect of l <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> 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.

References

12