mlsanityData to 7 Oct 2026

Normality-Calibrated Autoencoder for Unsupervised Anomaly Detection on Data Contamination

arXiv 2110.14825 ↗First posted 28 Oct 2021cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose Normality-Calibrated Autoencoder (NCAE), which can boost anomaly detection performance on the contaminated datasets without any prior information or explicit abnormal samples in the training phase. The NCAE adversarially generates high confident normal samples from a latent space having low entropy and leverages them to predict abnormal samples in a training dataset. NCAE is trained to minimise reconstruction errors in uncontaminated samples and maximise reconstruction errors in contaminated samples. The experimental results demonstrate that our method outperforms shallow, hybrid, and deep methods for unsupervised anomaly detection and achieves comparable performance compared with semi-supervised methods using labelled anomaly samples in the training phase. The source code is publicly available on `https://github.com/andreYoo/NCAE_UAD.git'.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 25 of its 62 references that are in the map. First posted on arXiv 28 Oct 2021.

Builds on

25 of 62 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  3. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  4. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  5. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  6. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  7. 2019Deep Learning for Anomaly Detection: A Surveycited by 357
  8. 2019Deep Semi-Supervised Anomaly Detectioncited by 290
  9. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  10. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
  11. 2019Deep Anomaly Detection with Deviation Networkscited by 152
  12. 2016Deep Structured Energy Based Models for Anomaly Detectioncited by 113
13 more
  1. 2017PacGAN: The power of two samples in generative adversarial networkscited by 104
  2. 2021Contrastive Learning with Stronger Augmentationscited by 100
  3. 2018Generative Probabilistic Novelty Detection with Adversarial Autoencoderscited by 99
  4. 2020Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detectioncited by 83
  5. 2014Toward Supervised Anomaly Detectioncited by 73
  6. 2020Anomaly Detection with Density Estimationcited by 71
  7. 2021Feature Encoding with AutoEncoders for Weakly-supervised Anomaly Detectioncited by 42
  8. 2017Unsupervised and Semi-supervised Anomaly Detection with LSTM Neural Networkscited by 40
  9. 2019Robust Anomaly Detection in Images using Adversarial Autoencoderscited by 38
  10. 2019Robust Subspace Recovery Layer for Unsupervised Anomaly Detectioncited by 31
  11. 2021Autoencoding Under Normalization Constraintscited by 26
  12. 2019Unsupervised Learning of Anomaly Detection from Contaminated Image Data using Simultaneous Encoder Trainingcited by 9
  13. 2020OneFlow: One-class flow for anomaly detection based on a minimal volume regioncited by 9

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 0; 2025: 2.

5 papers.

  1. 2023An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contaminationcited by 4
  2. 2023Unsupervised Deep One-Class Classification with Adaptive Threshold based on Training Dynamicscited by 1
  3. 2022Deep Anomaly Detection and Search via Reinforcement Learningcited by 0
  4. 2025Anomaly Detection with Adaptive and Aggressive Rejection for Contaminated Training Datacited by 0
  5. 2025Hybrid Quantum-Classical Autoencoders for Unsupervised Network Intrusion Detectioncited by 0