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

arXiv: https://arxiv.org/abs/1802.00187 · HTML: https://mlsanity.com/paper/1802.00187/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Feb 2018.

## Built on by (most cited first, 17 of 17)

- [VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization](https://mlsanity.com/paper/2104.10036/) (2021)
- [Student-Teacher Feature Pyramid Matching for Anomaly Detection](https://mlsanity.com/paper/2103.04257/) (2021)
- [In Defense of Core-set: A Density-aware Core-set Selection for Active Learning](https://mlsanity.com/paper/2206.04838/) (2022)
- [Consensus Synergizes with Memory: A Simple Approach for Anomaly Segmentation in Urban Scenes](https://mlsanity.com/paper/2111.15463/) (2021)
- [SeMAnD: Self-Supervised Anomaly Detection in Multimodal Geospatial Datasets](https://mlsanity.com/paper/2309.15245/) (2023)
- [GDFlow: Anomaly Detection with NCDE-based Normalizing Flow for Advanced Driver Assistance System](https://mlsanity.com/paper/2409.05346/) (2024)
- [An Unsupervised Deep-Learning Method for Fingerprint Classification: the CCAE Network and the Hybrid Clustering Strategy](https://mlsanity.com/paper/2109.05526/) (2021)
- [Classification Auto-Encoder based Detector against Diverse Data Poisoning Attacks](https://mlsanity.com/paper/2108.04206/) (2021)
- [on the effectiveness of generative adversarial network on anomaly detection](https://mlsanity.com/paper/2112.15541/) (2021)
- [Towards a Unified Framework of Clustering-based Anomaly Detection](https://mlsanity.com/paper/2406.00452/) (2024)
- [Fitbeat: COVID-19 Estimation based on Wristband Heart Rate](https://mlsanity.com/paper/2104.09263/) (2021)
- [Concise Logarithmic Loss Function for Robust Training of Anomaly Detection Model](https://mlsanity.com/paper/2201.05748/) (2022)
- [Diminishing Empirical Risk Minimization for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2205.14676/) (2022)
- [Unsupervised Anomaly Detection via Nonlinear Manifold Learning](https://mlsanity.com/paper/2306.09441/) (2023)
- [Cross-Modality Clustering-based Self-Labeling for Multimodal Data Classification](https://mlsanity.com/paper/2408.02568/) (2024)
- [Mutual Information Surprise: Rethinking Unexpectedness in Autonomous Systems](https://mlsanity.com/paper/2508.17403/) (2025)
- [Unsupervised Anomaly Detection with an Enhanced Teacher for Student-Teacher Feature Pyramid Matching](https://mlsanity.com/paper/2512.18219/) (2025)

## Abstract (arXiv)

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.