Clustering and Unsupervised Anomaly Detection with L2 Normalized Deep Auto-Encoder Representations
arXiv:1802.00187
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.
Submitted to IJCNN 2018
References in corpus (2)
Cited by in corpus (10)
- Deep Learning for Anomaly Detection: A Survey
- Hyperspherical Variational Auto-Encoders
- Gaussian Mixture Generative Adversarial Networks for Diverse Datasets, and the Unsupervised Clustering of Images
- Robust Subspace Recovery Layer for Unsupervised Anomaly Detection
- Deep learning models for predictive maintenance: a survey, comparison, challenges and prospect
- Open Set Recognition with Conditional Probabilistic Generative Models
- Novelty Detection via Robust Variational Autoencoding
- Rare Event Detection using Disentangled Representation Learning
- Fitbeat: COVID-19 Estimation based on Wristband Heart Rate
- Classification Auto-Encoder based Detector against Diverse Data Poisoning Attacks