mlsanityData to 7 Oct 2026

Robust Subspace Recovery Layer for Unsupervised Anomaly Detection

arXiv 1904.00152 ↗First posted 30 Mar 2019cs.LG cs.CV stat.MLcited by 31

Not on the map. Why?

Abstract (arXiv)

We propose a neural network for unsupervised anomaly detection with a novel robust subspace recovery layer (RSR layer). This layer seeks to extract the underlying subspace from a latent representation of the given data and removes outliers that lie away from this subspace. It is used within an autoencoder. The encoder maps the data into a latent space, from which the RSR layer extracts the subspace. The decoder then smoothly maps back the underlying subspace to a "manifold" close to the original inliers. Inliers and outliers are distinguished according to the distances between the original and mapped positions (small for inliers and large for outliers). Extensive numerical experiments with both image and document datasets demonstrate state-of-the-art precision and recall.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 8; 2023: 6; 2024: 4; 2025: 2; 2026: 1.

31 papers.

Sort:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2021One-Class Classification: A Surveycited by 35
  3. 2021Self-supervise, Refine, Repeat: Improving Unsupervised Anomaly Detectioncited by 20
  4. 2022Adaptive Model Pooling for Online Deep Anomaly Detection from a Complex Evolving Data Streamcited by 13
  5. 2021Unsupervised Outlier Detection using Memory and Contrastive Learningcited by 11
  6. 2021Anomaly Detection: How to Artificially Increase your F1-Score with a Biased Evaluation Protocolcited by 9
  7. 2021Enhancing Unsupervised Anomaly Detection with Score-Guided Networkcited by 8
  8. 2023METER: A Dynamic Concept Adaptation Framework for Online Anomaly Detectioncited by 8
  9. 2021Probabilistic Robust Autoencoders for Outlier Detectioncited by 7
  10. 2023ODIM: Outlier Detection via Likelihood of Under-Fitted Generative Modelscited by 6
  11. 2021Normality-Calibrated Autoencoder for Unsupervised Anomaly Detection on Data Contaminationcited by 5
  12. 2022Towards an Awareness of Time Series Anomaly Detection Models' Adversarial Vulnerabilitycited by 5
19 more
  1. 2024Revisiting Deep Feature Reconstruction for Logical and Structural Industrial Anomaly Detectioncited by 5
  2. 2022Robust Vector Quantized-Variational Autoencodercited by 4
  3. 2023An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contaminationcited by 4
  4. 2022Unsupervised Anomaly Detection for Auditing Data and Impact of Categorical Encodingscited by 3
  5. 2023GRAM: An Interpretable Approach for Graph Anomaly Detection using Gradient Attention Mapscited by 3
  6. 2021SLA2P: Self-supervised Anomaly Detection with Adversarial Perturbationcited by 2
  7. 2024Detecting Abnormal Operations in Concentrated Solar Power Plants from Irregular Sequences of Thermal Imagescited by 2
  8. 2021FiSH: Fair Spatial Hotspotscited by 1
  9. 2022TPAD: Identifying Effective Trajectory Predictions Under the Guidance of Trajectory Anomaly Detection Modelcited by 1
  10. 2022Repairing Systematic Outliers by Learning Clean Subspaces in VAEscited by 1
  11. 2023Unsupervised Deep One-Class Classification with Adaptive Threshold based on Training Dynamicscited by 1
  12. 2024A Robust Autoencoder Ensemble-Based Approach for Anomaly Detection in Textcited by 1
  13. 2022Diminishing Empirical Risk Minimization for Unsupervised Anomaly Detectioncited by 0
  14. 2022Anomaly segmentation model for defects detection in electroluminescence images of heterojunction solar cellscited by 0
  15. 2023MSS-PAE: Saving Autoencoder-based Outlier Detection from Unexpected Reconstructioncited by 0
  16. 2024Rethinking Unsupervised Outlier Detection via Multiple Thresholdingcited by 0
  17. 2025MSD-LLM: Predicting Ship Detention in Port State Control Inspections with Large Language Modelcited by 0
  18. 2025Unsupervised Feature Selection via Robust Autoencoder and Adaptive Graph Learningcited by 0
  19. 2026Catching Every Ripple: Enhanced Anomaly Awareness via Dynamic Concept Adaptationcited by 0